Skip to content

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

blog(mission): 2 new posts from run-20260911-1114

chaitanyagiri24a905983fa8
diff --git a/blog/media-src/spec.js b/blog/media-src/spec.js
index f88b5c7c..ca0c9686 100644
--- a/blog/media-src/spec.js
+++ b/blog/media-src/spec.js
@@ -28,6 +28,8 @@ const SPEC = {
"how-to-add-an-mcp-server-to-claude-code": { a: "wire", blue: "claude mcp add", orange: "one command, three scopes" },
"codex-cli-vs-claude-code": { a: "versus", blue: "codex cli", blue2: "claude code", orange: "same job, two dials" },
"how-much-does-claude-code-cost": { a: "ledger", blue: "pro · max · api", orange: "what the bill really says" },
+ "how-to-use-claude-code-plan-mode": { a: "guard", amber: "risky edits", blue: "permission mode: plan", orange: "read first, edit after yes" },
+ "what-is-an-mcp-server": { a: "routing", amber: "requests", blue: "mcp", orange: "one plug, many tools" },
"compressing-agent-memory": { a: "memory", blue: "compress, keep the original", orange: "smaller memory, no loss" },
"conductor-claude-code-alternative": { a: "versus", blue: "conductor", blue2: "munder difflin", orange: "a conductor alternative" },
"context-engineering-for-ai-agents": { a: "ledger", blue: "the context window is a budget", orange: "spend it deliberately" },
diff --git a/blog/src/_data/media.json b/blog/src/_data/media.json
index 85ead832..792e2996 100644
--- a/blog/src/_data/media.json
+++ b/blog/src/_data/media.json
@@ -600,6 +600,31 @@
},
"youtube": []
},
+ "codex-cli-vs-claude-code": {
+ "title": "Codex CLI vs Claude Code",
+ "category": "comparisons",
+ "hero": {
+ "file": "assets/media/codex-cli-vs-claude-code/hero.png",
+ "alt": "Illustration: Codex CLI vs Claude Code",
+ "prompt": "Hero image for a blog post titled \"Codex CLI vs Claude Code\". The post is about: Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.",
+ "status": "ready"
+ },
+ "inline": {
+ "note-1": {
+ "file": "assets/media/codex-cli-vs-claude-code/note-1.png",
+ "alt": "Hand-drawn sketch from “Codex CLI vs Claude Code”",
+ "prompt": "",
+ "status": "ready"
+ },
+ "note-2": {
+ "file": "assets/media/codex-cli-vs-claude-code/note-2.png",
+ "alt": "Hand-drawn sketch from “Codex CLI vs Claude Code”",
+ "prompt": "",
+ "status": "ready"
+ }
+ },
+ "youtube": []
+ },
"command-center-guide": {
"title": "The Command Center: Kanban, Fleet, and Budgets in One Place",
"category": "guides",
@@ -1150,6 +1175,31 @@
},
"youtube": []
},
+ "how-much-does-claude-code-cost": {
+ "title": "How Much Does Claude Code Cost?",
+ "category": "concepts",
+ "hero": {
+ "file": "assets/media/how-much-does-claude-code-cost/hero.png",
+ "alt": "Illustration: How Much Does Claude Code Cost?",
+ "prompt": "Hero image for a blog post titled \"How Much Does Claude Code Cost?\". The post is about: What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.",
+ "status": "ready"
+ },
+ "inline": {
+ "note-1": {
+ "file": "assets/media/how-much-does-claude-code-cost/note-1.png",
+ "alt": "Hand-drawn sketch from “How Much Does Claude Code Cost?”",
+ "prompt": "",
+ "status": "ready"
+ },
+ "note-2": {
+ "file": "assets/media/how-much-does-claude-code-cost/note-2.png",
+ "alt": "Hand-drawn sketch from “How Much Does Claude Code Cost?”",
+ "prompt": "",
+ "status": "ready"
+ }
+ },
+ "youtube": []
+ },
"how-the-god-orchestrator-works": {
"title": "Inside the GOD Orchestrator: Routing, Adjudication, Escalation",
"category": "orchestration",
@@ -1200,6 +1250,31 @@
},
"youtube": []
},
+ "how-to-add-an-mcp-server-to-claude-code": {
+ "title": "How to Add an MCP Server to Claude Code",
+ "category": "guides",
+ "hero": {
+ "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png",
+ "alt": "Illustration: How to Add an MCP Server to Claude Code",
+ "prompt": "Hero image for a blog post titled \"How to Add an MCP Server to Claude Code\". The post is about: The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.",
+ "status": "ready"
+ },
+ "inline": {
+ "note-1": {
+ "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/note-1.png",
+ "alt": "Hand-drawn sketch from “How to Add an MCP Server to Claude Code”",
+ "prompt": "",
+ "status": "ready"
+ },
+ "note-2": {
+ "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/note-2.png",
+ "alt": "Hand-drawn sketch from “How to Add an MCP Server to Claude Code”",
+ "prompt": "",
+ "status": "ready"
+ }
+ },
+ "youtube": []
+ },
"how-to-choose-a-multi-agent-tool": {
"title": "How to Choose a Multi-Agent Coding Tool: A Buyer's Checklist",
"category": "comparisons",
@@ -1409,6 +1484,31 @@
},
"youtube": []
},
+ "how-to-use-claude-code-plan-mode": {
+ "title": "How to Use Claude Code Plan Mode",
+ "category": "guides",
+ "hero": {
+ "file": "assets/media/how-to-use-claude-code-plan-mode/hero.png",
+ "alt": "Illustration: How to Use Claude Code Plan Mode",
+ "prompt": "Hero image for a blog post titled \"How to Use Claude Code Plan Mode\". The post is about: How Claude Code's plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.",
+ "status": "ready"
+ },
+ "inline": {
+ "note-1": {
+ "file": "assets/media/how-to-use-claude-code-plan-mode/note-1.png",
+ "alt": "Hand-drawn sketch from “How to Use Claude Code Plan Mode”",
+ "prompt": "",
+ "status": "ready"
+ },
+ "note-2": {
+ "file": "assets/media/how-to-use-claude-code-plan-mode/note-2.png",
+ "alt": "Hand-drawn sketch from “How to Use Claude Code Plan Mode”",
+ "prompt": "",
+ "status": "ready"
+ }
+ },
+ "youtube": []
+ },
"how-to-use-the-built-in-monaco-ide": {
"title": "How to Use the Built-in Monaco IDE",
"category": "guides",
@@ -3146,6 +3246,31 @@
},
"youtube": []
},
+ "what-is-an-mcp-server": {
+ "title": "What Is an MCP Server?",
+ "category": "concepts",
+ "hero": {
+ "file": "assets/media/what-is-an-mcp-server/hero.png",
+ "alt": "Illustration: What Is an MCP Server?",
+ "prompt": "Hero image for a blog post titled \"What Is an MCP Server?\". The post is about: An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.",
+ "status": "ready"
+ },
+ "inline": {
+ "note-1": {
+ "file": "assets/media/what-is-an-mcp-server/note-1.png",
+ "alt": "Hand-drawn sketch from “What Is an MCP Server?”",
+ "prompt": "",
+ "status": "ready"
+ },
+ "note-2": {
+ "file": "assets/media/what-is-an-mcp-server/note-2.png",
+ "alt": "Hand-drawn sketch from “What Is an MCP Server?”",
+ "prompt": "",
+ "status": "ready"
+ }
+ },
+ "youtube": []
+ },
"what-is-harness-engineering": {
"title": "What Is Harness Engineering?",
"category": "concepts",
@@ -3407,80 +3532,5 @@
"status": "placeholder"
}
]
- },
- "how-to-add-an-mcp-server-to-claude-code": {
- "title": "How to Add an MCP Server to Claude Code",
- "category": "guides",
- "hero": {
- "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png",
- "alt": "Illustration: How to Add an MCP Server to Claude Code",
- "prompt": "Hero image for a blog post titled \"How to Add an MCP Server to Claude Code\". The post is about: The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.",
- "status": "ready"
- },
- "inline": {
- "note-1": {
- "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/note-1.png",
- "alt": "Hand-drawn sketch from “How to Add an MCP Server to Claude Code”",
- "prompt": "",
- "status": "ready"
- },
- "note-2": {
- "file": "assets/media/how-to-add-an-mcp-server-to-claude-code/note-2.png",
- "alt": "Hand-drawn sketch from “How to Add an MCP Server to Claude Code”",
- "prompt": "",
- "status": "ready"
- }
- },
- "youtube": []
- },
- "codex-cli-vs-claude-code": {
- "title": "Codex CLI vs Claude Code",
- "category": "comparisons",
- "hero": {
- "file": "assets/media/codex-cli-vs-claude-code/hero.png",
- "alt": "Illustration: Codex CLI vs Claude Code",
- "prompt": "Hero image for a blog post titled \"Codex CLI vs Claude Code\". The post is about: Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.",
- "status": "ready"
- },
- "inline": {
- "note-1": {
- "file": "assets/media/codex-cli-vs-claude-code/note-1.png",
- "alt": "Hand-drawn sketch from “Codex CLI vs Claude Code”",
- "prompt": "",
- "status": "ready"
- },
- "note-2": {
- "file": "assets/media/codex-cli-vs-claude-code/note-2.png",
- "alt": "Hand-drawn sketch from “Codex CLI vs Claude Code”",
- "prompt": "",
- "status": "ready"
- }
- },
- "youtube": []
- },
- "how-much-does-claude-code-cost": {
- "title": "How Much Does Claude Code Cost?",
- "category": "concepts",
- "hero": {
- "file": "assets/media/how-much-does-claude-code-cost/hero.png",
- "alt": "Illustration: How Much Does Claude Code Cost?",
- "prompt": "Hero image for a blog post titled \"How Much Does Claude Code Cost?\". The post is about: What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.",
- "status": "ready"
- },
- "inline": {
- "note-1": {
- "file": "assets/media/how-much-does-claude-code-cost/note-1.png",
- "alt": "Hand-drawn sketch from “How Much Does Claude Code Cost?”",
- "prompt": "",
- "status": "ready"
- },
- "note-2": {
- "file": "assets/media/how-much-does-claude-code-cost/note-2.png",
- "alt": "Hand-drawn sketch from “How Much Does Claude Code Cost?”",
- "prompt": "",
- "status": "ready"
- }
- },
- "youtube": []
}
}
diff --git a/blog/src/assets/media/how-to-use-claude-code-plan-mode/hero.png b/blog/src/assets/media/how-to-use-claude-code-plan-mode/hero.png
new file mode 100644
index 00000000..6ddf9015
Binary files /dev/null and b/blog/src/assets/media/how-to-use-claude-code-plan-mode/hero.png differ
diff --git a/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-1.png b/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-1.png
new file mode 100644
index 00000000..d368b59c
Binary files /dev/null and b/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-1.png differ
diff --git a/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-2.png b/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-2.png
new file mode 100644
index 00000000..fa377a75
Binary files /dev/null and b/blog/src/assets/media/how-to-use-claude-code-plan-mode/note-2.png differ
diff --git a/blog/src/assets/media/what-is-an-mcp-server/hero.png b/blog/src/assets/media/what-is-an-mcp-server/hero.png
new file mode 100644
index 00000000..350d8b79
Binary files /dev/null and b/blog/src/assets/media/what-is-an-mcp-server/hero.png differ
diff --git a/blog/src/assets/media/what-is-an-mcp-server/note-1.png b/blog/src/assets/media/what-is-an-mcp-server/note-1.png
new file mode 100644
index 00000000..cfe09aeb
Binary files /dev/null and b/blog/src/assets/media/what-is-an-mcp-server/note-1.png differ
diff --git a/blog/src/assets/media/what-is-an-mcp-server/note-2.png b/blog/src/assets/media/what-is-an-mcp-server/note-2.png
new file mode 100644
index 00000000..fe07f15e
Binary files /dev/null and b/blog/src/assets/media/what-is-an-mcp-server/note-2.png differ
diff --git a/blog/src/posts/agent-security-and-sandboxing.md b/blog/src/posts/agent-security-and-sandboxing.md
index 653c8c20..98eb07da 100644
--- a/blog/src/posts/agent-security-and-sandboxing.md
+++ b/blog/src/posts/agent-security-and-sandboxing.md
@@ -48,7 +48,7 @@ spawns each agent with `--permission-mode bypassPermissions`. The onboarding flo
That honesty is the right framing. Bypass mode isn't reckless — it's the *correct* default for an
unattended control room. But it removes the last interactive gate, so the safety has to live somewhere
-else. The rest of this post is "somewhere else."
+else. The rest of this post is "somewhere else." One side effect worth knowing: a bypass session also skips plan mode's edit block, as [how to use Claude Code plan mode](/blog/how-to-use-claude-code-plan-mode/) explains.
{% img "note-1" %}
diff --git a/blog/src/posts/how-to-add-an-mcp-server-to-claude-code.md b/blog/src/posts/how-to-add-an-mcp-server-to-claude-code.md
index 5c81636e..9e345234 100644
--- a/blog/src/posts/how-to-add-an-mcp-server-to-claude-code.md
+++ b/blog/src/posts/how-to-add-an-mcp-server-to-claude-code.md
@@ -29,7 +29,7 @@ That one command handles the common case. What's worth understanding is the scop
## What is an MCP server?
-An MCP server is a program that gives an agent tools or data it doesn't have built in: a way to search issues, query a database, or drive a browser. The Model Context Protocol is the open standard those servers speak, described on its own site as "a standardized way to connect AI applications to external systems" (checked 10 Sep 2026, [modelcontextprotocol.io](https://modelcontextprotocol.io)). Anthropic open sourced MCP on 25 November 2024, with initial SDKs and a handful of reference servers (checked 10 Sep 2026, [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol)). Claude Code is one client among several now; any compliant server works with it.
+An MCP server is a program that gives an agent tools or data it doesn't have built in: a way to search issues, query a database, or drive a browser. The Model Context Protocol is the open standard those servers speak, described on its own site as "a standardized way to connect AI applications to external systems" (checked 10 Sep 2026, [modelcontextprotocol.io](https://modelcontextprotocol.io)). Anthropic open sourced MCP on 25 November 2024, with initial SDKs and a handful of reference servers (checked 10 Sep 2026, [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol)). Claude Code is one client among several now; any compliant server works with it. For the longer answer, with the host, client and server roles and how discovery works, see [What Is an MCP Server?](/blog/what-is-an-mcp-server/).
## How do you add an MCP server to Claude Code?
diff --git a/blog/src/posts/how-to-use-claude-code-plan-mode.md b/blog/src/posts/how-to-use-claude-code-plan-mode.md
new file mode 100644
index 00000000..714e60df
--- /dev/null
+++ b/blog/src/posts/how-to-use-claude-code-plan-mode.md
@@ -0,0 +1,76 @@
+---
+title: "How to Use Claude Code Plan Mode"
+description: "How Claude Code's plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it."
+date: 2026-09-11
+category: guides
+categoryLabel: Guides
+type: Technical
+primaryKeyword: "how to use claude code plan mode"
+secondaryKeywords: ["how to use claude code plan mode effectively", "how to enable claude code plan mode", "how to exit claude code plan mode", "claude code plan mode shortcut", "claude code plan mode vs accept edits", "should i use claude code plan mode"]
+tags: ["Guides", "Claude Code", "Getting Started", "Human-in-the-Loop"]
+faq:
+ - q: "What is Claude Code plan mode?"
+ a: "It is one of Claude Code's permission modes. Claude reads files and runs shell commands to explore, then writes a plan, but does not edit your source. The official docs put it plainly: plan mode tells Claude to research and propose changes without making them, and edits stay blocked until you approve the plan."
+ - q: "How do you enable plan mode in Claude Code?"
+ a: "Press Shift+Tab during a session to cycle to it, prefix a single prompt with /plan, or start the session already in it with claude --permission-mode plan. The same flag works with -p for headless runs, so scripts and CI steps can start in plan mode too."
+ - q: "How do you exit plan mode?"
+ a: "Press Shift+Tab again to leave without approving anything, or approve the plan, which exits plan mode for you. The prompt offers Yes, and use auto mode (Yes, auto-accept edits when auto mode is unavailable), Yes, manually approve edits, or No, keep planning, which keeps you in plan mode so you can redirect Claude."
+ - q: "Can plan mode edit files?"
+ a: "No. Plan mode blocks edits to your source until you approve the plan, even when you ask for the edit directly, and in our headless run Claude declined exactly that request. It does write the plan itself, by default under ~/.claude/plans/ (the plansDirectory setting can move it). The exception is a session started with bypass permissions available, for example with --dangerously-skip-permissions or --allow-dangerously-skip-permissions: Claude is still told to plan, but an edit it attempts then runs without prompting."
+ - q: "What is the difference between plan mode and accept edits mode?"
+ a: "Accept edits mode auto-approves file writes and common filesystem commands like mkdir and mv, so you review changes afterward. Plan mode is the phase before that: read and explore only, meant to run first so you can approve or redirect the plan before anything gets written."
+ - q: "Should you use plan mode for every task?"
+ a: "No. Claude Code's own best practices docs, checked 11 Sep 2026, say planning matters most when you're uncertain about the approach, the change touches multiple files, or you don't know the code well, and that you can skip it when you could describe the diff in one sentence. For a small, obvious fix, just ask Claude to make it directly."
+---
+
+<div class="callout tldr"><span class="ic">TL;DR</span><p>Turn on <strong>plan mode</strong> with <code>claude --permission-mode plan</code>, the <code>/plan</code> prefix, or <code>Shift+Tab</code> until the status bar shows plan mode on. Claude reads your codebase and shell output but cannot edit your source, and writes a plan you read before approving it. Approving switches the session to auto mode (accept edits when auto mode is unavailable) or to approving each edit yourself; <code>Shift+Tab</code> again leaves without approving anything. The same flag works with <code>-p</code>, though a headless run has no approval prompt: it just writes the plan and exits.</p></div>
+
+Plan mode is a Claude Code permission mode that makes Claude read your codebase and write a plan before it touches a single file. Turn it on with `claude --permission-mode plan`, the `/plan` prefix, or by pressing Shift+Tab until the status bar shows plan mode on. Nothing gets edited until you approve what it wrote.
+
+The rest of this covers how the mode actually behaves, which commands run without asking while it plans, and what a headless run with `--permission-mode plan` really prints, since most writeups describe the behavior without pasting any output. Running several Claude Code sessions at once makes this matter more: a plan per session is one document to read before anything changes, not several diffs to untangle after ([manage multiple Claude Code sessions](/blog/manage-multiple-claude-code-sessions/)).
+
+## How do you turn on plan mode in Claude Code?
+
+Three ways, and they all land in the same mode. Press Shift+Tab during a session to cycle to it (the cycle runs `default`, `acceptEdits`, `plan`, then `bypassPermissions` and `auto` if they're available, then back to `default`; Pro, Max and Team sessions start in `auto`, so plan mode is three presses away), prefix a single prompt with `/plan`, or start the session already in it with `claude --permission-mode plan` (checked 11 Sep 2026, [Choose a permission mode](https://code.claude.com/docs/en/permission-modes)). The same flag works with `-p` for non-interactive runs.
+
+## What does plan mode actually let Claude do?
+
+Reads, mostly, and not much else. The docs describe it as telling "Claude to research and propose changes without making them. Claude reads files, runs shell commands to explore, and writes a plan, but does not edit your source" (checked 11 Sep 2026, [Choose a permission mode](https://code.claude.com/docs/en/permission-modes)). When auto mode is available and the `useAutoModeDuringPlan` setting is on, which it is by default, a classifier reviews the shell commands Claude wants to run while it plans, instead of prompting you for each one; when auto mode isn't available, anything past the built-in read-only command set still prompts as usual.
+
+{% img "note-1" %}
+
+## What does a plan mode run actually print?
+
+We made a two-function `hello.py` in a scratch folder on 11 Sep 2026 and ran Claude Code with `-p --permission-mode plan`, first asking for a suggestion, then asking directly for an edit to see whether plan mode holds:
+
+```
+$ claude --version
+2.1.268 (Claude Code)
+
+$ claude -p --permission-mode plan "Add a multiply function to hello.py right now, actually edit the file."
+I haven't edited `hello.py` yet. Plan mode is on, and it blocks every file change except the plan file, even when you ask me to edit right away. I also can't switch plan mode off from here: the tool for that isn't available in this session.
+...
+The plan is saved at `~/.claude/plans/add-a-multiply-function-buzzing-dolphin.md`. It includes a one-line `python3` check that `multiply(3, 4) == 12`, and that `add` and `subtract` still work.
+
+Turn plan mode off (Shift+Tab in the CLI, or restart without plan mode) and tell me to go ahead, and I'll make the edit and run the check.
+```
+
+Told to actually edit the file, it wrote a memo about the edit instead. Fitting, for a paper company's blog.
+
+The first prompt, "Read `hello.py` and suggest one small refactor. Do not edit any files.", told Claude not to edit, so it proves less: it printed type-hinted versions of both functions, wrote its plan to `~/.claude/plans/`, and left `hello.py` untouched. The second run above is the real test: asked directly to edit, it still didn't: it read `hello.py`, wrote the plan and never attempted an edit, with no approval prompt to accept.
+
+## How do you get out of plan mode?
+
+Two ways: reject everything with another Shift+Tab, or approve the plan, which exits plan mode for you. When the plan is ready, the CLI asks how to proceed: Yes, and use auto mode (it reads Yes, auto-accept edits when auto mode is unavailable), Yes, manually approve edits, or No, keep planning, which keeps you in plan mode so you can redirect Claude (checked 11 Sep 2026, [Choose a permission mode](https://code.claude.com/docs/en/permission-modes)). Press Ctrl+G first if you'd rather open the plan in your own text editor and change it before Claude proceeds.
+
+{% img "note-2" %}
+
+## Does plan mode work the same in scripts, not just the terminal?
+
+Partly. Plan mode applies in a `-p` run, but there's no approval step: Claude writes the plan, prints its summary, and exits, as the run above shows. Claude Code's own headless docs are direct about the default: "the built-in starting permission mode is Manual on every plan, so pass the permission mode you want" (checked 11 Sep 2026, [Run Claude Code programmatically](https://code.claude.com/docs/en/headless)), unless a project's `permissions.defaultMode` setting already sets `plan`. Passing `--permission-mode plan` in a CI step gets you a proposed change with no edits. Set `plansDirectory` to a path inside the project (the default is `~/.claude/plans`) so a later step can upload the plan for review, the same gate as [approving AI agents without a queue](/blog/human-in-the-loop-approving-ai-agents/).
+
+## Plan mode vs accept edits mode: which do you actually want?
+
+Different phases of the same job, not competitors. `acceptEdits` mode auto-approves file writes and common filesystem commands like `mkdir` and `mv`, so you review changes afterward in `git diff`; plan mode blocks the edits and hands you a document to read first. Claude Code's best practices page says planning is most useful "when you're uncertain about the approach, when the change modifies multiple files, or when you're unfamiliar with the code being modified" (checked 11 Sep 2026, [Best practices](https://code.claude.com/docs/en/best-practices)). If you only want to gate one risky command rather than a whole session, [Claude Code's hooks](/blog/claude-code-hooks-explained/) can block a single tool call.
+
+None of this needs Munder Difflin. Each Claude Code agent on the floor is a real `claude` process, but as of Munder Difflin 0.5.2, Auto Mode is on by default and starts it with `--permission-mode bypassPermissions`, and in a session like that Claude Code does not enforce plan mode's blocks (checked 11 Sep 2026, [Choose a permission mode](https://code.claude.com/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode)). Turn Auto Mode off and restart the agent if you want plan mode to hold for your Claude Code agents. [Download Munder Difflin](https://munderdiffl.in/download) to try it, the classic office is free, and [pricing](https://munderdiffl.in/#pricing) covers the paid plans.
diff --git a/blog/src/posts/what-is-an-mcp-server.md b/blog/src/posts/what-is-an-mcp-server.md
new file mode 100644
index 00000000..72aacaf3
--- /dev/null
+++ b/blog/src/posts/what-is-an-mcp-server.md
@@ -0,0 +1,90 @@
+---
+title: "What Is an MCP Server?"
+description: "An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in."
+date: 2026-09-11
+category: concepts
+categoryLabel: Concepts
+type: Technical
+primaryKeyword: "what is an mcp server"
+secondaryKeywords: ["how does an mcp server work", "mcp server vs api", "what does mcp server mean", "what does mcp stand for", "mcp server claude code"]
+tags: ["Concepts", "MCP", "Claude Code", "Getting Started"]
+faq:
+ - q: "What does MCP stand for?"
+ a: "Model Context Protocol, the open standard an AI application uses to reach tools, data and prompt templates it does not have built in. Anthropic open sourced it on 25 November 2024, and the specification you would read today is dated 2026-07-28."
+ - q: "Why use an MCP server instead of a plain API?"
+ a: "A plain API needs its own client code written by hand for every application that wants to call it. An MCP server lists its own tools when a client asks, in a shape any MCP host already understands, so the same server works in Claude Code, an IDE or a chat app without custom glue for each one."
+ - q: "Can an MCP server access the internet?"
+ a: "Yes, if its own code does. An MCP server is an ordinary program, local or remote, and either kind can read files, run commands or call whatever APIs it is written to call. The protocol does not limit what a server can do, only how it talks to the client."
+ - q: "What is an MCP server in Claude?"
+ a: "The same thing as anywhere else: a program that gives Claude tools, data or prompts over MCP. Claude Code and Claude Desktop can run a local server on your machine, while a custom connector on claude.ai has to be a remote server reached over HTTP. Anthropic's connector docs also list MCP features Claude does not support yet, such as resource subscriptions, and set a different tool result limit for claude.ai than for Claude Code, so a server can behave differently from one Claude surface to the next (checked 11 Sep 2026, claude.com/docs/connectors/building)."
+ - q: "Does every AI coding agent support MCP servers?"
+ a: "Many do. The protocol's own site names Claude, ChatGPT, Visual Studio Code and Cursor among the applications that support it, and its architecture page names Claude Code as an example host (checked 11 Sep 2026, modelcontextprotocol.io). Support for each feature and the setup screen still vary, so check a given agent's docs before assuming a server will show up the same way."
+---
+
+<div class="callout tldr"><span class="ic">TL;DR</span><p>An <strong>MCP server</strong> is a small program that hands an AI agent tools, data or prompt templates over the <strong>Model Context Protocol</strong>, an open standard. The agent's app (the <strong>host</strong>) opens a <strong>client</strong> connection to each server it uses, the two talk in JSON-RPC over stdio or Streamable HTTP, and the server answers with whatever it was built to expose. One server, many hosts, no custom glue code.</p></div>
+
+An MCP server is a small program that gives an AI agent access to something it doesn't have built in: a database, an issue tracker, a browser, your files. It speaks the Model Context Protocol, an open standard, so any compliant AI application can connect the same way, without custom code to wire each one up.
+
+If you already use one AI coding CLI, this layer matters more once you run several agents at once in a [multi-agent harness](/blog/what-is-a-multi-agent-harness/), because each agent reaches its databases and issue trackers through the servers it has been given, and which agent gets which server becomes your call.
+
+## What is an MCP server?
+
+It's a program that exposes tools, data or prompt templates to an AI application over the Model Context Protocol. The protocol's own site describes it as an open standard for connecting AI applications to external systems (checked 11 Sep 2026, [modelcontextprotocol.io](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro)). Anthropic open sourced MCP on 25 November 2024 (checked 11 Sep 2026, [Introducing the Model Context Protocol](https://www.anthropic.com/news/model-context-protocol)), and it's grown well past Anthropic's own tools since: the protocol's own site names ChatGPT, Visual Studio Code and Cursor among the applications that support it.
+
+The official framing is a USB-C port for AI applications: one connector shape instead of a different adapter for every device. It's a fair comparison, and a relief if you remember the drawer full of proprietary chargers that preceded USB-C.
+
+{% img "note-1" %}
+
+## How does an MCP server work?
+
+Three roles do the work: a host, a client and a server. The **host** is the AI application, Claude Code or Claude Desktop, say. It opens one **client** for every server it connects to, and each client keeps a dedicated connection to its server (checked 11 Sep 2026, [MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture)). Client and server exchange JSON-RPC 2.0 messages, and the spec says MCP takes some inspiration from the Language Server Protocol that editors use for programming languages (checked 11 Sep 2026, [MCP specification](https://modelcontextprotocol.io/specification/2026-07-28)). Those messages travel over one of two transports: stdio for a server running as a local process, or Streamable HTTP for one running remotely, which typically serves many clients at once.
+
+A client can ask a server which protocol versions and features it supports with one `server/discover` request, then fetch the actual tools, resources and prompts with `tools/list`, `resources/list` and `prompts/list`, and those lists can change while you work (checked 11 Sep 2026, [MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture)).
+
+## What does an MCP server actually give an agent?
+
+Three things, formally called primitives: tools, resources and prompts. **Tools** are functions the agent can call to do something, like running a query or filing a ticket. **Resources** are data the agent can read for context, like a file's contents or a database record. **Prompts** are ready made templates the user picks, often shown as slash commands ([MCP server concepts](https://modelcontextprotocol.io/docs/2026-07-28/learn/server-concepts)), so a server can ship its own few-shot examples alongside its tools (checked 11 Sep 2026, [MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture)).
+
+Claude Code is one MCP host among several, and not every host handles all three: client and server each declare what they support, so check your client's docs (checked 11 Sep 2026, [MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture)). Here's the Claude Code command that manages those servers from the client side, checked on 11 Sep 2026:
+
+```bash
+$ claude --version
+2.1.268 (Claude Code)
+
+$ claude mcp --help
+Usage: claude mcp [options] [command]
+
+Configure and manage MCP servers
+
+Options:
+ -h, --help Display help for command
+
+Commands:
+ add [options] <name> <commandOrUrl> [args...] Add an MCP server to Claude Code.
+ ...
+ list List configured MCP servers. Unapproved
+ .mcp.json servers are shown as ⏸ Pending
+ approval and not connected to; approved
+ servers are health-checked unless
+ disabled for this project.
+ ...
+ remove [options] <name> Remove an MCP server
+ ...
+ serve [options] Start the Claude Code MCP server
+```
+
+The full help screen lists eleven subcommands and `add`'s own usage examples; this excerpt cuts to what matters here (the `...` lines mark where). `add` is the client side, wiring a server in; `list` shows what's configured and health-checks the approved servers; `serve` runs Claude Code itself as a server, the same binary on both ends of the protocol. For the actual walkthrough, [adding an MCP server to Claude Code](/blog/how-to-add-an-mcp-server-to-claude-code/) covers the scope flag, the `.mcp.json` file it writes and how to pass an API key.
+
+{% img "note-2" %}
+
+## What is the difference between an MCP server and an API?
+
+An API is a fixed contract you integrate against by reading its docs and writing client code once, for that one API. An MCP server lists its own tools for any client that asks, in a shape every MCP host already understands, so the same server plugs into Claude Code, an IDE or a chat app with no per app glue. Underneath, many MCP servers wrap an existing API; MCP is the layer that makes the tool discoverable and callable by a model without you writing that translation each time.
+
+## Does an MCP server run locally, or does it need the internet?
+
+Either, and the choice belongs to the server, not the protocol. A local server using the stdio transport runs on your own machine, commonly one client at a time, with no network hop at all, which is how the filesystem or a local database server usually ships. A remote server using Streamable HTTP runs on someone else's infrastructure and can serve many clients at once, the way a hosted issue tracker or CRM server would (checked 11 Sep 2026, [MCP architecture](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture)).
+
+Whichever way a server runs, the spec says descriptions of tool behavior "should be considered untrusted, unless obtained from a trusted server" (checked 11 Sep 2026, [MCP specification](https://modelcontextprotocol.io/specification/2026-07-28)). That's exactly the opening [MCP's known attacks](/blog/mcp-security-tool-poisoning/) work through, so approve a server because you've read what it does, not on reflex.
+
+In Munder Difflin 0.5.2, Pro's Capabilities screen gives each server an on or off switch per Claude Code agent, and a server rated write or secret stays off until you turn it on yourself. The grant reaches Claude Code agents only, so Codex and the other CLIs on the floor don't get servers from it. MCP itself doesn't need Munder Difflin: `claude mcp add` is Claude Code's own command, and MCP is an open standard either way. [Download Munder Difflin](https://munderdiffl.in/download) for the free classic office, or see [what Pro adds](https://munderdiffl.in/#pricing) for per-agent control over servers like these.
diff --git a/docs/blog/agent-security-and-sandboxing/index.html b/docs/blog/agent-security-and-sandboxing/index.html
index 26e3e7a5..fbf02e50 100644
--- a/docs/blog/agent-security-and-sandboxing/index.html
+++ b/docs/blog/agent-security-and-sandboxing/index.html
@@ -190,7 +190,7 @@ foot-gun on production repos.</p>
</blockquote>
<p>That honesty is the right framing. Bypass mode isn’t reckless — it’s the <em>correct</em> default for an
unattended control room. But it removes the last interactive gate, so the safety has to live somewhere
-else. The rest of this post is “somewhere else.”</p>
+else. The rest of this post is “somewhere else.” One side effect worth knowing: a bypass session also skips plan mode’s edit block, as <a href="/blog/how-to-use-claude-code-plan-mode/">how to use Claude Code plan mode</a> explains.</p>
<figure class="fig fig-inline"><img src="/blog/assets/media/agent-security-and-sandboxing/note-1.png" alt="Hand-drawn sketch from “Running AI Agents Safely: Permission Modes and Sandboxing”" loading="lazy" decoding="async" /></figure>
<h2 id="when-the-prompt-is-off-structure-is-your-safety" tabindex="-1">When the prompt is off, structure is your safety <a class="anchor" href="#when-the-prompt-is-off-structure-is-your-safety" aria-hidden="true">#</a></h2>
<p>If you can’t rely on a human clicking “approve,” you make the dangerous things structurally hard to
@@ -308,50 +308,50 @@ git, lifecycle hooks, and an audit trail — so safe-by-default is the path of l
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/agents-rule-of-two/index.html b/docs/blog/agents-rule-of-two/index.html
index beebff08..a6886b2e 100644
--- a/docs/blog/agents-rule-of-two/index.html
+++ b/docs/blog/agents-rule-of-two/index.html
@@ -312,50 +312,50 @@ open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/ai-agent-glossary/index.html b/docs/blog/ai-agent-glossary/index.html
index b7156099..d7fe9dc2 100644
--- a/docs/blog/ai-agent-glossary/index.html
+++ b/docs/blog/ai-agent-glossary/index.html
@@ -284,50 +284,50 @@ Munder Difflin</a> to see the glossary come to life — free and open source.</p
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png
new file mode 100644
index 00000000..6ddf9015
Binary files /dev/null and b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png differ
diff --git a/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-1.png b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-1.png
new file mode 100644
index 00000000..d368b59c
Binary files /dev/null and b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-1.png differ
diff --git a/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-2.png b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-2.png
new file mode 100644
index 00000000..fa377a75
Binary files /dev/null and b/docs/blog/assets/media/how-to-use-claude-code-plan-mode/note-2.png differ
diff --git a/docs/blog/assets/media/what-is-an-mcp-server/hero.png b/docs/blog/assets/media/what-is-an-mcp-server/hero.png
new file mode 100644
index 00000000..350d8b79
Binary files /dev/null and b/docs/blog/assets/media/what-is-an-mcp-server/hero.png differ
diff --git a/docs/blog/assets/media/what-is-an-mcp-server/note-1.png b/docs/blog/assets/media/what-is-an-mcp-server/note-1.png
new file mode 100644
index 00000000..cfe09aeb
Binary files /dev/null and b/docs/blog/assets/media/what-is-an-mcp-server/note-1.png differ
diff --git a/docs/blog/assets/media/what-is-an-mcp-server/note-2.png b/docs/blog/assets/media/what-is-an-mcp-server/note-2.png
new file mode 100644
index 00000000..fe07f15e
Binary files /dev/null and b/docs/blog/assets/media/what-is-an-mcp-server/note-2.png differ
diff --git a/docs/blog/building-reliable-ai-agents/index.html b/docs/blog/building-reliable-ai-agents/index.html
index e4c75b33..700589b2 100644
--- a/docs/blog/building-reliable-ai-agents/index.html
+++ b/docs/blog/building-reliable-ai-agents/index.html
@@ -339,50 +339,50 @@ by design; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/can-claude-code-agents-talk-to-each-other/index.html b/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
index 1e51404c..82c8beda 100644
--- a/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
+++ b/docs/blog/can-claude-code-agents-talk-to-each-other/index.html
@@ -322,50 +322,50 @@ other; it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/claude-code-automation-while-you-sleep/index.html b/docs/blog/claude-code-automation-while-you-sleep/index.html
index abec5c89..dfdbfc9c 100644
--- a/docs/blog/claude-code-automation-while-you-sleep/index.html
+++ b/docs/blog/claude-code-automation-while-you-sleep/index.html
@@ -327,50 +327,50 @@ while you sleep; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html
index ff382115..7252f965 100644
--- a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html
+++ b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html
@@ -316,50 +316,50 @@ coordinated team of Claude Code agents — it’s free, local, and open source.<
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html
index 53a7fef8..5ac1c1d4 100644
--- a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html
+++ b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html
@@ -358,50 +358,50 @@ open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/codex-cli-vs-claude-code/index.html b/docs/blog/codex-cli-vs-claude-code/index.html
index f9873402..26b4e325 100644
--- a/docs/blog/codex-cli-vs-claude-code/index.html
+++ b/docs/blog/codex-cli-vs-claude-code/index.html
@@ -249,7 +249,7 @@ rereads. If you already pay for Claude, that is a lot of control for no extra se
<footer class="post-foot wrap"><div class="prevnext">
<a class="pn prev" href="/blog/how-much-does-claude-code-cost/"><span class="k">← Older</span><span class="t">How Much Does Claude Code Cost?</span></a>
- <span></span>
+ <a class="pn next" href="/blog/what-is-an-mcp-server/"><span class="k">Newer →</span><span class="t">What Is an MCP Server?</span></a>
</div>
<section class="related">
<h2>Related in Comparisons</h2>
diff --git a/docs/blog/command-center-guide/index.html b/docs/blog/command-center-guide/index.html
index 8ca4b044..7d1c516b 100644
--- a/docs/blog/command-center-guide/index.html
+++ b/docs/blog/command-center-guide/index.html
@@ -308,50 +308,50 @@ place in your morning routine, <a href="https://github.com/chaitanyagiri/munder-
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-hire-from-the-agent-gallery/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-hire-from-the-agent-gallery/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-hire-from-the-agent-gallery/">How to Hire From the Agent Gallery</a></h3>
- <p class="dek">A practical guide to Munder Difflin&#39;s Agent Gallery: pick one of 80 ready made roles, download its manifest, import it with Add agent, review every field, customise identity, workspace, engine and briefing, then spawn it yourself.</p>
+ <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
+ <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-hire-from-the-agent-gallery/" aria-label="Read: How to Hire From the Agent Gallery">Read →</a>
+ <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/context-engineering-for-ai-agents/index.html b/docs/blog/context-engineering-for-ai-agents/index.html
index 8fed7807..53129e37 100644
--- a/docs/blog/context-engineering-for-ai-agents/index.html
+++ b/docs/blog/context-engineering-for-ai-agents/index.html
@@ -344,50 +344,50 @@ it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/debugging-multi-agent-systems/index.html b/docs/blog/debugging-multi-agent-systems/index.html
index fd840296..14e358b8 100644
--- a/docs/blog/debugging-multi-agent-systems/index.html
+++ b/docs/blog/debugging-multi-agent-systems/index.html
@@ -307,50 +307,50 @@ to run agents you can actually trace; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/do-more-with-less-model-routing/index.html b/docs/blog/do-more-with-less-model-routing/index.html
index 259a3261..4ccad25b 100644
--- a/docs/blog/do-more-with-less-model-routing/index.html
+++ b/docs/blog/do-more-with-less-model-routing/index.html
@@ -311,50 +311,50 @@ agent team that does more with less — it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html b/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html
index db004b90..edca7072 100644
--- a/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html
+++ b/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html
@@ -302,50 +302,50 @@ rides your existing Claude subscription. Local-first, on your own plan, no surpr
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/evaluating-ai-agent-reliability/index.html b/docs/blog/evaluating-ai-agent-reliability/index.html
index f4113360..a5053ddd 100644
--- a/docs/blog/evaluating-ai-agent-reliability/index.html
+++ b/docs/blog/evaluating-ai-agent-reliability/index.html
@@ -310,50 +310,50 @@ your bar.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/feed.xml b/docs/blog/feed.xml
index 6983831c..22ea6248 100644
--- a/docs/blog/feed.xml
+++ b/docs/blog/feed.xml
@@ -4,9 +4,25 @@
<subtitle>Guides, deep dives, and comparisons on running multi-agent Claude Code: orchestration, agent memory, automation, and the tooling landscape.</subtitle>
<link href="https://munderdiffl.in/blog/feed.xml" rel="self" />
<link href="https://munderdiffl.in/blog/" />
- <updated>2026-09-10T00:00:00.000Z</updated>
+ <updated>2026-09-11T00:00:00.000Z</updated>
<id>https://munderdiffl.in/blog/</id>
<author><name>Chaitanya Giri</name><uri>https://munderdiffl.in</uri></author>
+ <entry>
+ <title>How to Use Claude Code Plan Mode</title>
+ <link href="https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" />
+ <id>https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/</id>
+ <published>2026-09-11T00:00:00.000Z</published>
+ <updated>2026-09-11T00:00:00.000Z</updated><category term="Guides" />
+ <summary>How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</summary>
+ </entry>
+ <entry>
+ <title>What Is an MCP Server?</title>
+ <link href="https://munderdiffl.in/blog/what-is-an-mcp-server/" />
+ <id>https://munderdiffl.in/blog/what-is-an-mcp-server/</id>
+ <published>2026-09-11T00:00:00.000Z</published>
+ <updated>2026-09-11T00:00:00.000Z</updated><category term="Concepts" />
+ <summary>An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</summary>
+ </entry>
<entry>
<title>Codex CLI vs Claude Code</title>
<link href="https://munderdiffl.in/blog/codex-cli-vs-claude-code/" />
@@ -471,20 +487,4 @@
<updated>2026-06-05T00:00:00.000Z</updated><category term="Internals" />
<summary>How and why to compress an agent&#39;s long-term memory: the toolbox, the lossy trap, and keeping a lossless original beside a compact copy.</summary>
</entry>
- <entry>
- <title>Generative Engine Optimization: The Techniques the Research Backs</title>
- <link href="https://munderdiffl.in/blog/generative-engine-optimization-techniques/" />
- <id>https://munderdiffl.in/blog/generative-engine-optimization-techniques/</id>
- <published>2026-06-05T00:00:00.000Z</published>
- <updated>2026-06-05T00:00:00.000Z</updated><category term="Concepts" />
- <summary>What the first peer-reviewed GEO study found works to get content cited by AI — statistics, source citations, quotes — and why keyword stuffing backfires.</summary>
- </entry>
- <entry>
- <title>How to Install and Use Munder Difflin: A Beginner&#39;s Guide</title>
- <link href="https://munderdiffl.in/blog/how-to-install-and-use-munder-difflin/" />
- <id>https://munderdiffl.in/blog/how-to-install-and-use-munder-difflin/</id>
- <published>2026-06-05T00:00:00.000Z</published>
- <updated>2026-09-10T00:00:00.000Z</updated><category term="Guides" />
- <summary>A plain language guide to Munder Difflin 0.5.2. What a coding agent is, which AI engine to pick based on what you already pay for, the one terminal command you&#39;ll ever run, and how to install and set it up on macOS, Windows or Linux.</summary>
- </entry>
</feed>
diff --git a/docs/blog/generative-engine-optimization-techniques/index.html b/docs/blog/generative-engine-optimization-techniques/index.html
index 78f4b72e..37718894 100644
--- a/docs/blog/generative-engine-optimization-techniques/index.html
+++ b/docs/blog/generative-engine-optimization-techniques/index.html
@@ -316,50 +316,50 @@ and quotable. <a href="/#install">Download Munder Difflin</a> to see it; free an
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-ai-agents-verify-their-own-work/index.html b/docs/blog/how-ai-agents-verify-their-own-work/index.html
index 99a1a75a..f72e8bba 100644
--- a/docs/blog/how-ai-agents-verify-their-own-work/index.html
+++ b/docs/blog/how-ai-agents-verify-their-own-work/index.html
@@ -310,50 +310,50 @@ and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-much-does-claude-code-cost/index.html b/docs/blog/how-much-does-claude-code-cost/index.html
index 61accd9b..ca6c6fbc 100644
--- a/docs/blog/how-much-does-claude-code-cost/index.html
+++ b/docs/blog/how-much-does-claude-code-cost/index.html
@@ -257,50 +257,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/voice-as-a-control-plane-for-agent-fleets/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/voice-as-a-control-plane-for-agent-fleets/">Voice Is a Control Plane, Not a Gimmick</a></h3>
- <p class="dek">Voice is a terrible way to write code and a great way to run a fleet. Why low-bandwidth commands over high-bandwidth work is the right split — with Munder Difflin&#39;s Talk mode (echo-back confirmation, spend caps, michael-voice attribution) as the case study.</p>
+ <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
+ <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-label="Read: Voice Is a Control Plane, Not a Gimmick">Read →</a>
+ <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html b/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html
index 11617da9..7007a8f9 100644
--- a/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html
+++ b/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html
@@ -283,50 +283,50 @@
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-hire-from-the-agent-gallery/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-hire-from-the-agent-gallery/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-hire-from-the-agent-gallery/">How to Hire From the Agent Gallery</a></h3>
- <p class="dek">A practical guide to Munder Difflin&#39;s Agent Gallery: pick one of 80 ready made roles, download its manifest, import it with Add agent, review every field, customise identity, workspace, engine and briefing, then spawn it yourself.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-hire-from-the-agent-gallery/" aria-label="Read: How to Hire From the Agent Gallery">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html b/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html
index b7523e87..aec91d46 100644
--- a/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html
+++ b/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html
@@ -172,7 +172,7 @@
<p>You add an MCP server to Claude Code with one command: <code>claude mcp add</code>, a name you pick, and the command or URL that starts the server. Claude Code writes that entry to a config file, then loads the server’s tools the next time it reads it.</p>
<p>That one command handles the common case. What’s worth understanding is the scope flag, which decides who else sees the server, and the other ways to add one: editing <code>.mcp.json</code> yourself, or connecting from VS Code or the desktop app instead of the CLI. If you’re already running more than one Claude Code session, each reads the same project scoped servers, which is one less thing to juggle when you <a href="/blog/manage-multiple-claude-code-sessions/">manage multiple Claude Code sessions</a>.</p>
<h2 id="what-is-an-mcp-server" tabindex="-1">What is an MCP server? <a class="anchor" href="#what-is-an-mcp-server" aria-hidden="true">#</a></h2>
-<p>An MCP server is a program that gives an agent tools or data it doesn’t have built in: a way to search issues, query a database, or drive a browser. The Model Context Protocol is the open standard those servers speak, described on its own site as “a standardized way to connect AI applications to external systems” (checked 10 Sep 2026, <a href="https://modelcontextprotocol.io">modelcontextprotocol.io</a>). Anthropic open sourced MCP on 25 November 2024, with initial SDKs and a handful of reference servers (checked 10 Sep 2026, <a href="https://www.anthropic.com/news/model-context-protocol">Introducing the Model Context Protocol</a>). Claude Code is one client among several now; any compliant server works with it.</p>
+<p>An MCP server is a program that gives an agent tools or data it doesn’t have built in: a way to search issues, query a database, or drive a browser. The Model Context Protocol is the open standard those servers speak, described on its own site as “a standardized way to connect AI applications to external systems” (checked 10 Sep 2026, <a href="https://modelcontextprotocol.io">modelcontextprotocol.io</a>). Anthropic open sourced MCP on 25 November 2024, with initial SDKs and a handful of reference servers (checked 10 Sep 2026, <a href="https://www.anthropic.com/news/model-context-protocol">Introducing the Model Context Protocol</a>). Claude Code is one client among several now; any compliant server works with it. For the longer answer, with the host, client and server roles and how discovery works, see <a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a>.</p>
<h2 id="how-do-you-add-an-mcp-server-to-claude-code" tabindex="-1">How do you add an MCP server to Claude Code? <a class="anchor" href="#how-do-you-add-an-mcp-server-to-claude-code" aria-hidden="true">#</a></h2>
<p>Run <code>claude mcp add</code>, pick a name, and tell it what starts the server: a local command, or a URL with the transport flag set to <code>http</code> for a hosted one. Here’s what that looked like in a scratch folder, checked on 10 Sep 2026:</p>
<pre class="language-bash"><code class="language-bash">$ claude <span class="token parameter variable">--version</span>
@@ -291,50 +291,50 @@ terminal. A harness earns its place once several agents are running and only one
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-hire-from-the-agent-gallery/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-hire-from-the-agent-gallery/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-hire-from-the-agent-gallery/">How to Hire From the Agent Gallery</a></h3>
- <p class="dek">A practical guide to Munder Difflin&#39;s Agent Gallery: pick one of 80 ready made roles, download its manifest, import it with Add agent, review every field, customise identity, workspace, engine and briefing, then spawn it yourself.</p>
+ <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
+ <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-hire-from-the-agent-gallery/" aria-label="Read: How to Hire From the Agent Gallery">Read →</a>
+ <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-hire-from-the-agent-gallery/index.html b/docs/blog/how-to-hire-from-the-agent-gallery/index.html
index 97e9fa9a..87d2d23b 100644
--- a/docs/blog/how-to-hire-from-the-agent-gallery/index.html
+++ b/docs/blog/how-to-hire-from-the-agent-gallery/index.html
@@ -294,50 +294,50 @@ gallery page, then import it with Add agent and import hire. Manifests are plain
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-install-and-use-munder-difflin/index.html b/docs/blog/how-to-install-and-use-munder-difflin/index.html
index 0a0190c7..2313f252 100644
--- a/docs/blog/how-to-install-and-use-munder-difflin/index.html
+++ b/docs/blog/how-to-install-and-use-munder-difflin/index.html
@@ -624,50 +624,50 @@ stuck, the <a href="https://munderdiffl.in">Discord</a> is the fastest place to
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-run-multiple-claude-code-agents/index.html b/docs/blog/how-to-run-multiple-claude-code-agents/index.html
index c098536c..b9a1e2d5 100644
--- a/docs/blog/how-to-run-multiple-claude-code-agents/index.html
+++ b/docs/blog/how-to-run-multiple-claude-code-agents/index.html
@@ -251,50 +251,50 @@ free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-talk-to-your-orchestrator/index.html b/docs/blog/how-to-talk-to-your-orchestrator/index.html
index ffe1a8b0..dcbc41a4 100644
--- a/docs/blog/how-to-talk-to-your-orchestrator/index.html
+++ b/docs/blog/how-to-talk-to-your-orchestrator/index.html
@@ -274,50 +274,50 @@ Three goals in a trench coat. Split them — the task board handles dependencies
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/how-to-use-claude-code-plan-mode/index.html b/docs/blog/how-to-use-claude-code-plan-mode/index.html
new file mode 100644
index 00000000..54c688db
--- /dev/null
+++ b/docs/blog/how-to-use-claude-code-plan-mode/index.html
@@ -0,0 +1,373 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>How to Use Claude Code Plan Mode — Munder Difflin Blog</title>
+<meta name="description" content="How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it." />
+<link rel="canonical" href="https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="How to Use Claude Code Plan Mode — Munder Difflin Blog" />
+<meta property="og:description" content="How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it." />
+<meta property="og:url" content="https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-09-11T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Guides" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Getting Started" />
+<meta property="article:tag" content="Human-in-the-Loop" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="How to Use Claude Code Plan Mode — Munder Difflin Blog" />
+<meta name="twitter:description" content="How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&amp;family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&amp;family=Space+Grotesk:wght@500;600;700&amp;family=JetBrains+Mono:wght@400;600&amp;display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog-press.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "How to Use Claude Code Plan Mode",
+ "description": "How Claude Code's plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-09-11T00:00:00.000Z",
+ "dateModified": "2026-09-11T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" },
+ "keywords": "how to use claude code plan mode, how to use claude code plan mode effectively, how to enable claude code plan mode, how to exit claude code plan mode, claude code plan mode shortcut, claude code plan mode vs accept edits, should i use claude code plan mode",
+ "articleSection": "Guides",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "How to Use Claude Code Plan Mode", "item": "https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What is Claude Code plan mode?", "acceptedAnswer": { "@type": "Answer", "text": "It is one of Claude Code's permission modes. Claude reads files and runs shell commands to explore, then writes a plan, but does not edit your source. The official docs put it plainly: plan mode tells Claude to research and propose changes without making them, and edits stay blocked until you approve the plan." } },
+ { "@type": "Question", "name": "How do you enable plan mode in Claude Code?", "acceptedAnswer": { "@type": "Answer", "text": "Press Shift+Tab during a session to cycle to it, prefix a single prompt with /plan, or start the session already in it with claude --permission-mode plan. The same flag works with -p for headless runs, so scripts and CI steps can start in plan mode too." } },
+ { "@type": "Question", "name": "How do you exit plan mode?", "acceptedAnswer": { "@type": "Answer", "text": "Press Shift+Tab again to leave without approving anything, or approve the plan, which exits plan mode for you. The prompt offers Yes, and use auto mode (Yes, auto-accept edits when auto mode is unavailable), Yes, manually approve edits, or No, keep planning, which keeps you in plan mode so you can redirect Claude." } },
+ { "@type": "Question", "name": "Can plan mode edit files?", "acceptedAnswer": { "@type": "Answer", "text": "No. Plan mode blocks edits to your source until you approve the plan, even when you ask for the edit directly, and in our headless run Claude declined exactly that request. It does write the plan itself, by default under ~/.claude/plans/ (the plansDirectory setting can move it). The exception is a session started with bypass permissions available, for example with --dangerously-skip-permissions or --allow-dangerously-skip-permissions: Claude is still told to plan, but an edit it attempts then runs without prompting." } },
+ { "@type": "Question", "name": "What is the difference between plan mode and accept edits mode?", "acceptedAnswer": { "@type": "Answer", "text": "Accept edits mode auto-approves file writes and common filesystem commands like mkdir and mv, so you review changes afterward. Plan mode is the phase before that: read and explore only, meant to run first so you can approve or redirect the plan before anything gets written." } },
+ { "@type": "Question", "name": "Should you use plan mode for every task?", "acceptedAnswer": { "@type": "Answer", "text": "No. Claude Code's own best practices docs, checked 11 Sep 2026, say planning matters most when you're uncertain about the approach, the change touches multiple files, or you don't know the code well, and that you can skip it when you could describe the diff in one sentence. For a small, obvious fix, just ask Claude to make it directly." } }
+
+ ]
+}
+</script>
+
+
+<script>
+ // Anonymous blog analytics (PostHog) — same posture as the main site and the
+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only
+ // (person_profiles 'never'), no autocapture/recording, DNT respected.
+ (function () {
+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';
+ if (!PH_KEY || navigator.doNotTrack === '1') return;
+ var s = document.createElement('script');
+ s.async = true;
+ s.src = 'https://us-assets.i.posthog.com/static/array.js';
+ s.onload = function () {
+ if (!window.posthog) return;
+ window.posthog.init(PH_KEY, {
+ api_host: 'https://us.i.posthog.com',
+ person_profiles: 'never',
+ autocapture: false,
+ before_send: function (event) {
+ // PostHog fills $ip from the connection unless the event carries one.
+ // Null it here and disable the GeoIP lookup so no IP, city, postal
+ // code or lat/long is ever derived or stored for this page view.
+ if (event && event.properties) {
+ event.properties.$ip = null;
+ event.properties.$geoip_disable = true;
+ }
+ return event;
+ },
+ disable_session_recording: true,
+ respect_dnt: true
+ });
+ };
+ document.head.appendChild(s);
+ })();
+</script>
+</head>
+<body class="theme-press">
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article class="t-guides">
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/guides/">Guides</a>
+ </nav>
+ <h1>How to Use Claude Code Plan Mode</h1>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">MD</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Guides</span>
+ </div>
+ </header>
+
+ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="Illustration: How to Use Claude Code Plan Mode" loading="lazy" decoding="async" /></figure></div>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>Turn on <strong>plan mode</strong> with <code>claude --permission-mode plan</code>, the <code>/plan</code> prefix, or <code>Shift+Tab</code> until the status bar shows plan mode on. Claude reads your codebase and shell output but cannot edit your source, and writes a plan you read before approving it. Approving switches the session to auto mode (accept edits when auto mode is unavailable) or to approving each edit yourself; <code>Shift+Tab</code> again leaves without approving anything. The same flag works with <code>-p</code>, though a headless run has no approval prompt: it just writes the plan and exits.</p></div>
+<p>Plan mode is a Claude Code permission mode that makes Claude read your codebase and write a plan before it touches a single file. Turn it on with <code>claude --permission-mode plan</code>, the <code>/plan</code> prefix, or by pressing Shift+Tab until the status bar shows plan mode on. Nothing gets edited until you approve what it wrote.</p>
+<p>The rest of this covers how the mode actually behaves, which commands run without asking while it plans, and what a headless run with <code>--permission-mode plan</code> really prints, since most writeups describe the behavior without pasting any output. Running several Claude Code sessions at once makes this matter more: a plan per session is one document to read before anything changes, not several diffs to untangle after (<a href="/blog/manage-multiple-claude-code-sessions/">manage multiple Claude Code sessions</a>).</p>
+<h2 id="how-do-you-turn-on-plan-mode-in-claude-code" tabindex="-1">How do you turn on plan mode in Claude Code? <a class="anchor" href="#how-do-you-turn-on-plan-mode-in-claude-code" aria-hidden="true">#</a></h2>
+<p>Three ways, and they all land in the same mode. Press Shift+Tab during a session to cycle to it (the cycle runs <code>default</code>, <code>acceptEdits</code>, <code>plan</code>, then <code>bypassPermissions</code> and <code>auto</code> if they’re available, then back to <code>default</code>; Pro, Max and Team sessions start in <code>auto</code>, so plan mode is three presses away), prefix a single prompt with <code>/plan</code>, or start the session already in it with <code>claude --permission-mode plan</code> (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/permission-modes">Choose a permission mode</a>). The same flag works with <code>-p</code> for non-interactive runs.</p>
+<h2 id="what-does-plan-mode-actually-let-claude-do" tabindex="-1">What does plan mode actually let Claude do? <a class="anchor" href="#what-does-plan-mode-actually-let-claude-do" aria-hidden="true">#</a></h2>
+<p>Reads, mostly, and not much else. The docs describe it as telling “Claude to research and propose changes without making them. Claude reads files, runs shell commands to explore, and writes a plan, but does not edit your source” (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/permission-modes">Choose a permission mode</a>). When auto mode is available and the <code>useAutoModeDuringPlan</code> setting is on, which it is by default, a classifier reviews the shell commands Claude wants to run while it plans, instead of prompting you for each one; when auto mode isn’t available, anything past the built-in read-only command set still prompts as usual.</p>
+<figure class="fig fig-inline"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/note-1.png" alt="Hand-drawn sketch from “How to Use Claude Code Plan Mode”" loading="lazy" decoding="async" /></figure>
+<h2 id="what-does-a-plan-mode-run-actually-print" tabindex="-1">What does a plan mode run actually print? <a class="anchor" href="#what-does-a-plan-mode-run-actually-print" aria-hidden="true">#</a></h2>
+<p>We made a two-function <code>hello.py</code> in a scratch folder on 11 Sep 2026 and ran Claude Code with <code>-p --permission-mode plan</code>, first asking for a suggestion, then asking directly for an edit to see whether plan mode holds:</p>
+<pre><code>$ claude --version
+2.1.268 (Claude Code)
+
+$ claude -p --permission-mode plan &quot;Add a multiply function to hello.py right now, actually edit the file.&quot;
+I haven't edited `hello.py` yet. Plan mode is on, and it blocks every file change except the plan file, even when you ask me to edit right away. I also can't switch plan mode off from here: the tool for that isn't available in this session.
+...
+The plan is saved at `~/.claude/plans/add-a-multiply-function-buzzing-dolphin.md`. It includes a one-line `python3` check that `multiply(3, 4) == 12`, and that `add` and `subtract` still work.
+
+Turn plan mode off (Shift+Tab in the CLI, or restart without plan mode) and tell me to go ahead, and I'll make the edit and run the check.
+</code></pre>
+<p>Told to actually edit the file, it wrote a memo about the edit instead. Fitting, for a paper company’s blog.</p>
+<p>The first prompt, “Read <code>hello.py</code> and suggest one small refactor. Do not edit any files.”, told Claude not to edit, so it proves less: it printed type-hinted versions of both functions, wrote its plan to <code>~/.claude/plans/</code>, and left <code>hello.py</code> untouched. The second run above is the real test: asked directly to edit, it still didn’t: it read <code>hello.py</code>, wrote the plan and never attempted an edit, with no approval prompt to accept.</p>
+<h2 id="how-do-you-get-out-of-plan-mode" tabindex="-1">How do you get out of plan mode? <a class="anchor" href="#how-do-you-get-out-of-plan-mode" aria-hidden="true">#</a></h2>
+<p>Two ways: reject everything with another Shift+Tab, or approve the plan, which exits plan mode for you. When the plan is ready, the CLI asks how to proceed: Yes, and use auto mode (it reads Yes, auto-accept edits when auto mode is unavailable), Yes, manually approve edits, or No, keep planning, which keeps you in plan mode so you can redirect Claude (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/permission-modes">Choose a permission mode</a>). Press Ctrl+G first if you’d rather open the plan in your own text editor and change it before Claude proceeds.</p>
+<figure class="fig fig-inline"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/note-2.png" alt="Hand-drawn sketch from “How to Use Claude Code Plan Mode”" loading="lazy" decoding="async" /></figure>
+<h2 id="does-plan-mode-work-the-same-in-scripts-not-just-the-terminal" tabindex="-1">Does plan mode work the same in scripts, not just the terminal? <a class="anchor" href="#does-plan-mode-work-the-same-in-scripts-not-just-the-terminal" aria-hidden="true">#</a></h2>
+<p>Partly. Plan mode applies in a <code>-p</code> run, but there’s no approval step: Claude writes the plan, prints its summary, and exits, as the run above shows. Claude Code’s own headless docs are direct about the default: “the built-in starting permission mode is Manual on every plan, so pass the permission mode you want” (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/headless">Run Claude Code programmatically</a>), unless a project’s <code>permissions.defaultMode</code> setting already sets <code>plan</code>. Passing <code>--permission-mode plan</code> in a CI step gets you a proposed change with no edits. Set <code>plansDirectory</code> to a path inside the project (the default is <code>~/.claude/plans</code>) so a later step can upload the plan for review, the same gate as <a href="/blog/human-in-the-loop-approving-ai-agents/">approving AI agents without a queue</a>.</p>
+<h2 id="plan-mode-vs-accept-edits-mode-which-do-you-actually-want" tabindex="-1">Plan mode vs accept edits mode: which do you actually want? <a class="anchor" href="#plan-mode-vs-accept-edits-mode-which-do-you-actually-want" aria-hidden="true">#</a></h2>
+<p>Different phases of the same job, not competitors. <code>acceptEdits</code> mode auto-approves file writes and common filesystem commands like <code>mkdir</code> and <code>mv</code>, so you review changes afterward in <code>git diff</code>; plan mode blocks the edits and hands you a document to read first. Claude Code’s best practices page says planning is most useful “when you’re uncertain about the approach, when the change modifies multiple files, or when you’re unfamiliar with the code being modified” (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/best-practices">Best practices</a>). If you only want to gate one risky command rather than a whole session, <a href="/blog/claude-code-hooks-explained/">Claude Code’s hooks</a> can block a single tool call.</p>
+<p>None of this needs Munder Difflin. Each Claude Code agent on the floor is a real <code>claude</code> process, but as of Munder Difflin 0.5.2, Auto Mode is on by default and starts it with <code>--permission-mode bypassPermissions</code>, and in a session like that Claude Code does not enforce plan mode’s blocks (checked 11 Sep 2026, <a href="https://code.claude.com/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode">Choose a permission mode</a>). Turn Auto Mode off and restart the agent if you want plan mode to hold for your Claude Code agents. <a href="https://munderdiffl.in/download">Download Munder Difflin</a> to try it, the classic office is free, and <a href="https://munderdiffl.in/#pricing">pricing</a> covers the paid plans.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What is Claude Code plan mode?</p>
+ <p class="a">It is one of Claude Code&#39;s permission modes. Claude reads files and runs shell commands to explore, then writes a plan, but does not edit your source. The official docs put it plainly: plan mode tells Claude to research and propose changes without making them, and edits stay blocked until you approve the plan.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do you enable plan mode in Claude Code?</p>
+ <p class="a">Press Shift+Tab during a session to cycle to it, prefix a single prompt with /plan, or start the session already in it with claude --permission-mode plan. The same flag works with -p for headless runs, so scripts and CI steps can start in plan mode too.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">How do you exit plan mode?</p>
+ <p class="a">Press Shift+Tab again to leave without approving anything, or approve the plan, which exits plan mode for you. The prompt offers Yes, and use auto mode (Yes, auto-accept edits when auto mode is unavailable), Yes, manually approve edits, or No, keep planning, which keeps you in plan mode so you can redirect Claude.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Can plan mode edit files?</p>
+ <p class="a">No. Plan mode blocks edits to your source until you approve the plan, even when you ask for the edit directly, and in our headless run Claude declined exactly that request. It does write the plan itself, by default under ~/.claude/plans/ (the plansDirectory setting can move it). The exception is a session started with bypass permissions available, for example with --dangerously-skip-permissions or --allow-dangerously-skip-permissions: Claude is still told to plan, but an edit it attempts then runs without prompting.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What is the difference between plan mode and accept edits mode?</p>
+ <p class="a">Accept edits mode auto-approves file writes and common filesystem commands like mkdir and mv, so you review changes afterward. Plan mode is the phase before that: read and explore only, meant to run first so you can approve or redirect the plan before anything gets written.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Should you use plan mode for every task?</p>
+ <p class="a">No. Claude Code&#39;s own best practices docs, checked 11 Sep 2026, say planning matters most when you&#39;re uncertain about the approach, the change touches multiple files, or you don&#39;t know the code well, and that you can skip it when you could describe the diff in one sentence. For a small, obvious fix, just ask Claude to make it directly.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a><a class="tag" href="/blog/tags/human-in-the-loop/">Human-in-the-Loop</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#how-do-you-turn-on-plan-mode-in-claude-code">How do you turn on plan mode in Claude Code?</a></li><li class="lvl-2"><a href="#what-does-plan-mode-actually-let-claude-do">What does plan mode actually let Claude do?</a></li><li class="lvl-2"><a href="#what-does-a-plan-mode-run-actually-print">What does a plan mode run actually print?</a></li><li class="lvl-2"><a href="#how-do-you-get-out-of-plan-mode">How do you get out of plan mode?</a></li><li class="lvl-2"><a href="#does-plan-mode-work-the-same-in-scripts-not-just-the-terminal">Does plan mode work the same in scripts, not just the terminal?</a></li><li class="lvl-2"><a href="#plan-mode-vs-accept-edits-mode-which-do-you-actually-want">Plan mode vs accept edits mode: which do you actually want?</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/what-is-an-mcp-server/"><span class="k">← Older</span><span class="t">What Is an MCP Server?</span></a>
+ <span></span>
+ </div>
+ <section class="related">
+ <h2>Related in Guides</h2>
+ <div class="post-grid">
+ <article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-10">Sep 10, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-07-03">Jul 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-07-03">Jul 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
+ <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer class="site-foot">
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe
+ (function () {
+ document.addEventListener('click', function (e) {
+ var btn = e.target.closest('.yt-load');
+ if (!btn) return;
+ var box = btn.closest('.yt');
+ var id = box && box.getAttribute('data-yt');
+ if (!id) return;
+ var frame = document.createElement('iframe');
+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';
+ frame.title = box.getAttribute('data-title') || 'YouTube video';
+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';
+ frame.setAttribute('allowfullscreen', '');
+ box.replaceChildren(frame);
+ });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/how-to-use-the-built-in-monaco-ide/index.html b/docs/blog/how-to-use-the-built-in-monaco-ide/index.html
index dc070884..2e00f772 100644
--- a/docs/blog/how-to-use-the-built-in-monaco-ide/index.html
+++ b/docs/blog/how-to-use-the-built-in-monaco-ide/index.html
@@ -272,50 +272,50 @@
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/human-in-the-loop-approving-ai-agents/index.html b/docs/blog/human-in-the-loop-approving-ai-agents/index.html
index ca1e69da..9e4ba51c 100644
--- a/docs/blog/human-in-the-loop-approving-ai-agents/index.html
+++ b/docs/blog/human-in-the-loop-approving-ai-agents/index.html
@@ -307,50 +307,50 @@ you talk to? You can <a href="/#install">download Munder Difflin</a> free; it’
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/index.html b/docs/blog/index.html
index 081e62c2..092a4027 100644
--- a/docs/blog/index.html
+++ b/docs/blog/index.html
@@ -117,11 +117,11 @@
building a self-coordinating hive of agents with a GOD orchestrator you talk to.</p>
<div class="filters" role="navigation" aria-label="Topics">
- <a class="chip" aria-current="page">All<span class="ct">135</span></a>
+ <a class="chip" aria-current="page">All<span class="ct">137</span></a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
@@ -244,19 +244,19 @@
-<div class="wrap featured"><article class="card t-comparisons">
- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+<div class="wrap featured"><article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>
- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
- <span class="tag kind">Comparisons</span>
- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
@@ -268,6 +268,38 @@
<section class="wrap">
<div class="post-grid">
<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-comparisons">
+ <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-10">Sep 10, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>
+ <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>
+ <div class="foot">
+ <span class="tag kind">Comparisons</span>
+ <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
<a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/long-running-agents-the-2026-shift/index.html b/docs/blog/long-running-agents-the-2026-shift/index.html
index ef1ce3e9..4f6f62ad 100644
--- a/docs/blog/long-running-agents-the-2026-shift/index.html
+++ b/docs/blog/long-running-agents-the-2026-shift/index.html
@@ -330,50 +330,50 @@ source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/loop-engineering-for-ai-agents/index.html b/docs/blog/loop-engineering-for-ai-agents/index.html
index 46c3140f..258d8a51 100644
--- a/docs/blog/loop-engineering-for-ai-agents/index.html
+++ b/docs/blog/loop-engineering-for-ai-agents/index.html
@@ -272,50 +272,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/voice-as-a-control-plane-for-agent-fleets/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>4 min</span>
</div>
- <h3><a href="/blog/voice-as-a-control-plane-for-agent-fleets/">Voice Is a Control Plane, Not a Gimmick</a></h3>
- <p class="dek">Voice is a terrible way to write code and a great way to run a fleet. Why low-bandwidth commands over high-bandwidth work is the right split — with Munder Difflin&#39;s Talk mode (echo-back confirmation, spend caps, michael-voice attribution) as the case study.</p>
+ <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
+ <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-label="Read: Voice Is a Control Plane, Not a Gimmick">Read →</a>
+ <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/manage-multiple-claude-code-sessions/index.html b/docs/blog/manage-multiple-claude-code-sessions/index.html
index 6c2019e8..01bad8e9 100644
--- a/docs/blog/manage-multiple-claude-code-sessions/index.html
+++ b/docs/blog/manage-multiple-claude-code-sessions/index.html
@@ -304,50 +304,50 @@ isolated agents, shared memory, and a single committer, all on your own machine.
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/mcp-and-skills-in-a-hive/index.html b/docs/blog/mcp-and-skills-in-a-hive/index.html
index b0279dc5..4d7daf5a 100644
--- a/docs/blog/mcp-and-skills-in-a-hive/index.html
+++ b/docs/blog/mcp-and-skills-in-a-hive/index.html
@@ -320,50 +320,50 @@ existing setup into a coordinated team of agents; it’s free and open source.</
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/mcp-security-tool-poisoning/index.html b/docs/blog/mcp-security-tool-poisoning/index.html
index 1eeb858d..fc2c2eb3 100644
--- a/docs/blog/mcp-security-tool-poisoning/index.html
+++ b/docs/blog/mcp-security-tool-poisoning/index.html
@@ -309,50 +309,50 @@ execution. Do that and MCP is what it should be: a powerful, <em>bounded</em> wa
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/munder-difflin-faq/index.html b/docs/blog/munder-difflin-faq/index.html
index 6edb13c3..2e478570 100644
--- a/docs/blog/munder-difflin-faq/index.html
+++ b/docs/blog/munder-difflin-faq/index.html
@@ -301,50 +301,50 @@ free, open source, and local-first.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html b/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html
index 6ec14557..a9f0e953 100644
--- a/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html
+++ b/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html
@@ -285,50 +285,50 @@
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/open-source-ai-tools-on-purpose/index.html b/docs/blog/open-source-ai-tools-on-purpose/index.html
index 3b77a5c7..cbda63cc 100644
--- a/docs/blog/open-source-ai-tools-on-purpose/index.html
+++ b/docs/blog/open-source-ai-tools-on-purpose/index.html
@@ -303,50 +303,50 @@ autonomous. <a href="https://munderdiffl.in/#install">Download Munder Difflin</a
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/prompt-caching-for-ai-agents/index.html b/docs/blog/prompt-caching-for-ai-agents/index.html
index ff461d7b..0d30347d 100644
--- a/docs/blog/prompt-caching-for-ai-agents/index.html
+++ b/docs/blog/prompt-caching-for-ai-agents/index.html
@@ -339,50 +339,50 @@ that doesn’t waste your tokens; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/review-agent-work-where-it-happens/index.html b/docs/blog/review-agent-work-where-it-happens/index.html
index 69597ac3..b0f9d98a 100644
--- a/docs/blog/review-agent-work-where-it-happens/index.html
+++ b/docs/blog/review-agent-work-where-it-happens/index.html
@@ -263,50 +263,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/voice-as-a-control-plane-for-agent-fleets/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>5 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/voice-as-a-control-plane-for-agent-fleets/">Voice Is a Control Plane, Not a Gimmick</a></h3>
- <p class="dek">Voice is a terrible way to write code and a great way to run a fleet. Why low-bandwidth commands over high-bandwidth work is the right split — with Munder Difflin&#39;s Talk mode (echo-back confirmation, spend caps, michael-voice attribution) as the case study.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/voice-as-a-control-plane-for-agent-fleets/" aria-label="Read: Voice Is a Control Plane, Not a Gimmick">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/run-a-mixed-engine-office/index.html b/docs/blog/run-a-mixed-engine-office/index.html
index 103dbd81..782db04c 100644
--- a/docs/blog/run-a-mixed-engine-office/index.html
+++ b/docs/blog/run-a-mixed-engine-office/index.html
@@ -267,50 +267,50 @@
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/run-ai-agent-hive-from-slack-setup/index.html b/docs/blog/run-ai-agent-hive-from-slack-setup/index.html
index 69899814..6f7faed5 100644
--- a/docs/blog/run-ai-agent-hive-from-slack-setup/index.html
+++ b/docs/blog/run-ai-agent-hive-from-slack-setup/index.html
@@ -365,50 +365,50 @@ it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/run-munder-difflin-on-a-mac-mini/index.html b/docs/blog/run-munder-difflin-on-a-mac-mini/index.html
index e2c59564..931db716 100644
--- a/docs/blog/run-munder-difflin-on-a-mac-mini/index.html
+++ b/docs/blog/run-munder-difflin-on-a-mac-mini/index.html
@@ -400,50 +400,50 @@ machine awake while at least one agent is running.</li>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/run-munder-difflin-on-open-models/index.html b/docs/blog/run-munder-difflin-on-open-models/index.html
index 99f56614..df301b6e 100644
--- a/docs/blog/run-munder-difflin-on-open-models/index.html
+++ b/docs/blog/run-munder-difflin-on-open-models/index.html
@@ -515,50 +515,50 @@ and want the sizing walkthrough? Read the <a href="/blog/run-munder-difflin-on-a
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/security-for-ai-coding-agents/index.html b/docs/blog/security-for-ai-coding-agents/index.html
index 346e57d2..03d78816 100644
--- a/docs/blog/security-for-ai-coding-agents/index.html
+++ b/docs/blog/security-for-ai-coding-agents/index.html
@@ -304,50 +304,50 @@ and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/shareable-agent-roles/index.html b/docs/blog/shareable-agent-roles/index.html
index 9b0ff1a3..879d6d1c 100644
--- a/docs/blog/shareable-agent-roles/index.html
+++ b/docs/blog/shareable-agent-roles/index.html
@@ -305,50 +305,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/small-team-ai-agents-playbook/index.html b/docs/blog/small-team-ai-agents-playbook/index.html
index 3a1408d2..c30fe465 100644
--- a/docs/blog/small-team-ai-agents-playbook/index.html
+++ b/docs/blog/small-team-ai-agents-playbook/index.html
@@ -309,50 +309,50 @@ it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/tags/claude-code/index.html b/docs/blog/tags/claude-code/index.html
index 67141b28..885f7a8b 100644
--- a/docs/blog/tags/claude-code/index.html
+++ b/docs/blog/tags/claude-code/index.html
@@ -90,11 +90,43 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Claude Code</h1>
- <p class="lead">47 posts tagged <strong>Claude Code</strong>.</p>
+ <p class="lead">49 posts tagged <strong>Claude Code</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
- <article class="card t-comparisons">
+ <article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-comparisons">
<a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/tags/concepts/index.html b/docs/blog/tags/concepts/index.html
index f8ce037f..8dce25d5 100644
--- a/docs/blog/tags/concepts/index.html
+++ b/docs/blog/tags/concepts/index.html
@@ -90,11 +90,27 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Concepts</h1>
- <p class="lead">19 posts tagged <strong>Concepts</strong>.</p>
+ <p class="lead">20 posts tagged <strong>Concepts</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
<a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/tags/getting-started/index.html b/docs/blog/tags/getting-started/index.html
index e743c202..80b475c5 100644
--- a/docs/blog/tags/getting-started/index.html
+++ b/docs/blog/tags/getting-started/index.html
@@ -90,11 +90,43 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Getting Started</h1>
- <p class="lead">11 posts tagged <strong>Getting Started</strong>.</p>
+ <p class="lead">13 posts tagged <strong>Getting Started</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
- <article class="card t-concepts">
+ <article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
<a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/tags/guides/index.html b/docs/blog/tags/guides/index.html
index 21e8b6ee..ac3a46a2 100644
--- a/docs/blog/tags/guides/index.html
+++ b/docs/blog/tags/guides/index.html
@@ -90,11 +90,27 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Guides</h1>
- <p class="lead">24 posts tagged <strong>Guides</strong>.</p>
+ <p class="lead">25 posts tagged <strong>Guides</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-guides">
<a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/tags/human-in-the-loop/index.html b/docs/blog/tags/human-in-the-loop/index.html
index 3a0e268a..64dd402a 100644
--- a/docs/blog/tags/human-in-the-loop/index.html
+++ b/docs/blog/tags/human-in-the-loop/index.html
@@ -90,11 +90,27 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#Human-in-the-Loop</h1>
- <p class="lead">7 posts tagged <strong>Human-in-the-Loop</strong>.</p>
+ <p class="lead">8 posts tagged <strong>Human-in-the-Loop</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
<article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-guides">
<a class="thumb t-guides" href="/blog/how-to-talk-to-your-orchestrator/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-talk-to-your-orchestrator/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/tags/mcp/index.html b/docs/blog/tags/mcp/index.html
index 9068bd4d..a0c75e49 100644
--- a/docs/blog/tags/mcp/index.html
+++ b/docs/blog/tags/mcp/index.html
@@ -90,11 +90,27 @@
<header class="page-head wrap">
<p class="eyebrow">Tag</p>
<h1>#MCP</h1>
- <p class="lead">5 posts tagged <strong>MCP</strong>.</p>
+ <p class="lead">6 posts tagged <strong>MCP</strong>.</p>
</header>
<section class="wrap">
<div class="post-grid">
- <article class="card t-guides">
+ <article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-guides">
<a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
diff --git a/docs/blog/the-clone-army-trap-mixed-swarm-vs-identical-agents/index.html b/docs/blog/the-clone-army-trap-mixed-swarm-vs-identical-agents/index.html
index b699704c..90eff39b 100644
--- a/docs/blog/the-clone-army-trap-mixed-swarm-vs-identical-agents/index.html
+++ b/docs/blog/the-clone-army-trap-mixed-swarm-vs-identical-agents/index.html
@@ -339,50 +339,50 @@ source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/the-lethal-trifecta-for-coding-agents/index.html b/docs/blog/the-lethal-trifecta-for-coding-agents/index.html
index f212f426..9ea1a66a 100644
--- a/docs/blog/the-lethal-trifecta-for-coding-agents/index.html
+++ b/docs/blog/the-lethal-trifecta-for-coding-agents/index.html
@@ -327,50 +327,50 @@ secrets; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/the-multi-agent-cost-playbook/index.html b/docs/blog/the-multi-agent-cost-playbook/index.html
index 3900e781..f93210c4 100644
--- a/docs/blog/the-multi-agent-cost-playbook/index.html
+++ b/docs/blog/the-multi-agent-cost-playbook/index.html
@@ -309,50 +309,50 @@ to run a fleet that doesn’t bankrupt you — it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.html
index 6d5f60c3..28dfb1df 100644
--- a/docs/blog/topics/comparisons/index.html
+++ b/docs/blog/topics/comparisons/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.html
index 535ccfe7..721d329c 100644
--- a/docs/blog/topics/concepts/index.html
+++ b/docs/blog/topics/concepts/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
@@ -136,6 +136,22 @@
</div>
</div>
</article>
+<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card t-concepts">
<a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.html
index 8276b3f5..4d3aaea4 100644
--- a/docs/blog/topics/guides/index.html
+++ b/docs/blog/topics/guides/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
@@ -184,6 +184,22 @@
</div>
</div>
</article>
+<article class="card t-guides">
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
+ <div class="foot">
+ <span class="tag kind">Guides</span>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
+ </div>
+ </div>
+</article>
<article class="card t-guides">
<a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.html
index 37e9c15d..7ea628fa 100644
--- a/docs/blog/topics/index.html
+++ b/docs/blog/topics/index.html
@@ -102,7 +102,7 @@
<span class="thumb t-guides" aria-hidden="true">GUIDES</span>
<div class="body">
<h3 style="color:var(--ink)">guides</h3>
- <p class="dek">35 posts.</p>
+ <p class="dek">36 posts.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
</a>
@@ -111,7 +111,7 @@
<span class="thumb t-concepts" aria-hidden="true">CONCEPTS</span>
<div class="body">
<h3 style="color:var(--ink)">concepts</h3>
- <p class="dek">22 posts.</p>
+ <p class="dek">23 posts.</p>
<div class="foot"><span class="more">View topic →</span></div>
</div>
</a>
@@ -178,15 +178,15 @@
<a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">86</span></a>
- <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">47</span></a>
+ <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">49</span></a>
<a class="chip" href="/blog/tags/internals/">Internals<span class="ct">26</span></a>
- <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">24</span></a>
+ <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">25</span></a>
<a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">23</span></a>
- <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">19</span></a>
+ <a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">20</span></a>
<a class="chip" href="/blog/tags/orchestration/">Orchestration<span class="ct">19</span></a>
@@ -196,12 +196,12 @@
<a class="chip" href="/blog/tags/release/">Release<span class="ct">15</span></a>
+ <a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">13</span></a>
+
<a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">13</span></a>
<a class="chip" href="/blog/tags/automation/">Automation<span class="ct">12</span></a>
- <a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">11</span></a>
-
<a class="chip" href="/blog/tags/use-cases/">Use Cases<span class="ct">10</span></a>
<a class="chip" href="/blog/tags/tools/">Tools<span class="ct">10</span></a>
@@ -210,14 +210,16 @@
<a class="chip" href="/blog/tags/memory/">Memory<span class="ct">8</span></a>
- <a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">7</span></a>
+ <a class="chip" href="/blog/tags/human-in-the-loop/">Human-in-the-Loop<span class="ct">8</span></a>
- <a class="chip" href="/blog/tags/human-in-the-loop/">Human-in-the-Loop<span class="ct">7</span></a>
+ <a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">7</span></a>
<a class="chip" href="/blog/tags/security/">Security<span class="ct">7</span></a>
<a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">6</span></a>
+ <a class="chip" href="/blog/tags/mcp/">MCP<span class="ct">6</span></a>
+
<a class="chip" href="/blog/tags/hive/">Hive<span class="ct">6</span></a>
<a class="chip" href="/blog/tags/observability/">Observability<span class="ct">5</span></a>
@@ -226,8 +228,6 @@
<a class="chip" href="/blog/tags/electron/">Electron<span class="ct">5</span></a>
- <a class="chip" href="/blog/tags/mcp/">MCP<span class="ct">5</span></a>
-
<a class="chip" href="/blog/tags/autonomous/">Autonomous<span class="ct">5</span></a>
<a class="chip" href="/blog/tags/git/">Git<span class="ct">4</span></a>
diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.html
index acd9a855..fc77cee5 100644
--- a/docs/blog/topics/internals/index.html
+++ b/docs/blog/topics/internals/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">19</span></a>
diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.html
index 7b303b7f..72574d81 100644
--- a/docs/blog/topics/memory/index.html
+++ b/docs/blog/topics/memory/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.html
index b5de2c87..d50925a7 100644
--- a/docs/blog/topics/orchestration/index.html
+++ b/docs/blog/topics/orchestration/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.html
index f6ea2ab2..d631de29 100644
--- a/docs/blog/topics/story/index.html
+++ b/docs/blog/topics/story/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.html
index 195b2c8c..31145899 100644
--- a/docs/blog/topics/use-cases/index.html
+++ b/docs/blog/topics/use-cases/index.html
@@ -99,9 +99,9 @@
<div class="filters" role="navigation" aria-label="Topics">
<a class="chip" href="/blog/">All</a>
- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">35</span></a>
+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>
- <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">22</span></a>
+ <a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>
<a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>
diff --git a/docs/blog/trigger-ai-agents-from-github-webhook/index.html b/docs/blog/trigger-ai-agents-from-github-webhook/index.html
index 2e1a89fa..3f04ecfb 100644
--- a/docs/blog/trigger-ai-agents-from-github-webhook/index.html
+++ b/docs/blog/trigger-ai-agents-from-github-webhook/index.html
@@ -357,50 +357,50 @@ open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/trigger-ai-agents-from-slack/index.html b/docs/blog/trigger-ai-agents-from-slack/index.html
index 444b9e4e..dfb810e3 100644
--- a/docs/blog/trigger-ai-agents-from-slack/index.html
+++ b/docs/blog/trigger-ai-agents-from-slack/index.html
@@ -304,50 +304,50 @@ it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/voice-as-a-control-plane-for-agent-fleets/index.html b/docs/blog/voice-as-a-control-plane-for-agent-fleets/index.html
index 062a4ef1..f4d93e60 100644
--- a/docs/blog/voice-as-a-control-plane-for-agent-fleets/index.html
+++ b/docs/blog/voice-as-a-control-plane-for-agent-fleets/index.html
@@ -265,50 +265,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-are-claude-code-agents/index.html b/docs/blog/what-are-claude-code-agents/index.html
index 552c92a7..c54cc728 100644
--- a/docs/blog/what-are-claude-code-agents/index.html
+++ b/docs/blog/what-are-claude-code-agents/index.html
@@ -283,50 +283,50 @@ into an office; it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-a-multi-agent-harness/index.html b/docs/blog/what-is-a-multi-agent-harness/index.html
index bd968fac..8f551c5d 100644
--- a/docs/blog/what-is-a-multi-agent-harness/index.html
+++ b/docs/blog/what-is-a-multi-agent-harness/index.html
@@ -300,50 +300,50 @@ macOS, Windows or Linux and watch a coordinated team work an office floor.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-aeo-for-dev-tools/index.html b/docs/blog/what-is-aeo-for-dev-tools/index.html
index b099d00d..017db144 100644
--- a/docs/blog/what-is-aeo-for-dev-tools/index.html
+++ b/docs/blog/what-is-aeo-for-dev-tools/index.html
@@ -405,50 +405,50 @@ harness actually is</a>. Free and MIT-licensed.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-an-agent-development-environment/index.html b/docs/blog/what-is-an-agent-development-environment/index.html
index 9d64ea27..23868a42 100644
--- a/docs/blog/what-is-an-agent-development-environment/index.html
+++ b/docs/blog/what-is-an-agent-development-environment/index.html
@@ -268,50 +268,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/what-is-an-mcp-server/index.html b/docs/blog/what-is-an-mcp-server/index.html
new file mode 100644
index 00000000..28b6696b
--- /dev/null
+++ b/docs/blog/what-is-an-mcp-server/index.html
@@ -0,0 +1,381 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="UTF-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+<title>What Is an MCP Server? — Munder Difflin Blog</title>
+<meta name="description" content="An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in." />
+<link rel="canonical" href="https://munderdiffl.in/blog/what-is-an-mcp-server/" />
+
+<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />
+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />
+<meta name="theme-color" content="#F5F2E8" />
+
+<!-- Open Graph -->
+<meta property="og:site_name" content="Munder Difflin Blog" />
+<meta property="og:type" content="article" />
+<meta property="og:title" content="What Is an MCP Server? — Munder Difflin Blog" />
+<meta property="og:description" content="An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in." />
+<meta property="og:url" content="https://munderdiffl.in/blog/what-is-an-mcp-server/" />
+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />
+<meta property="og:locale" content="en_US" />
+<meta property="article:published_time" content="2026-09-11T00:00:00.000Z" />
+<meta property="article:author" content="Chaitanya Giri" />
+<meta property="article:tag" content="Concepts" />
+<meta property="article:tag" content="MCP" />
+<meta property="article:tag" content="Claude Code" />
+<meta property="article:tag" content="Getting Started" />
+
+
+<!-- Twitter -->
+<meta name="twitter:card" content="summary_large_image" />
+<meta name="twitter:title" content="What Is an MCP Server? — Munder Difflin Blog" />
+<meta name="twitter:description" content="An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in." />
+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />
+
+<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />
+<link rel="preconnect" href="https://fonts.googleapis.com" />
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&amp;family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&amp;family=Space+Grotesk:wght@500;600;700&amp;family=JetBrains+Mono:wght@400;600&amp;display=swap" rel="stylesheet" />
+<link rel="stylesheet" href="/blog/assets/blog-press.css" />
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BlogPosting",
+ "headline": "What Is an MCP Server?",
+ "description": "An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.",
+ "image": ["https://munderdiffl.in/media/og.png"],
+ "datePublished": "2026-09-11T00:00:00.000Z",
+ "dateModified": "2026-09-11T00:00:00.000Z",
+ "author": { "@type": "Person", "name": "Chaitanya Giri" },
+ "publisher": {
+ "@type": "Organization",
+ "name": "Munder Difflin",
+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }
+ },
+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/what-is-an-mcp-server/" },
+ "keywords": "what is an mcp server, how does an mcp server work, mcp server vs api, what does mcp server mean, what does mcp stand for, mcp server claude code",
+ "articleSection": "Concepts",
+ "inLanguage": "en-US",
+ "url": "https://munderdiffl.in/blog/what-is-an-mcp-server/"
+}
+</script>
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "BreadcrumbList",
+ "itemListElement": [
+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },
+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },
+ { "@type": "ListItem", "position": 3, "name": "What Is an MCP Server?", "item": "https://munderdiffl.in/blog/what-is-an-mcp-server/" }
+ ]
+}
+</script>
+
+<script type="application/ld+json">
+{
+ "@context": "https://schema.org",
+ "@type": "FAQPage",
+ "mainEntity": [
+ { "@type": "Question", "name": "What does MCP stand for?", "acceptedAnswer": { "@type": "Answer", "text": "Model Context Protocol, the open standard an AI application uses to reach tools, data and prompt templates it does not have built in. Anthropic open sourced it on 25 November 2024, and the specification you would read today is dated 2026-07-28." } },
+ { "@type": "Question", "name": "Why use an MCP server instead of a plain API?", "acceptedAnswer": { "@type": "Answer", "text": "A plain API needs its own client code written by hand for every application that wants to call it. An MCP server lists its own tools when a client asks, in a shape any MCP host already understands, so the same server works in Claude Code, an IDE or a chat app without custom glue for each one." } },
+ { "@type": "Question", "name": "Can an MCP server access the internet?", "acceptedAnswer": { "@type": "Answer", "text": "Yes, if its own code does. An MCP server is an ordinary program, local or remote, and either kind can read files, run commands or call whatever APIs it is written to call. The protocol does not limit what a server can do, only how it talks to the client." } },
+ { "@type": "Question", "name": "What is an MCP server in Claude?", "acceptedAnswer": { "@type": "Answer", "text": "The same thing as anywhere else: a program that gives Claude tools, data or prompts over MCP. Claude Code and Claude Desktop can run a local server on your machine, while a custom connector on claude.ai has to be a remote server reached over HTTP. Anthropic's connector docs also list MCP features Claude does not support yet, such as resource subscriptions, and set a different tool result limit for claude.ai than for Claude Code, so a server can behave differently from one Claude surface to the next (checked 11 Sep 2026, claude.com/docs/connectors/building)." } },
+ { "@type": "Question", "name": "Does every AI coding agent support MCP servers?", "acceptedAnswer": { "@type": "Answer", "text": "Many do. The protocol's own site names Claude, ChatGPT, Visual Studio Code and Cursor among the applications that support it, and its architecture page names Claude Code as an example host (checked 11 Sep 2026, modelcontextprotocol.io). Support for each feature and the setup screen still vary, so check a given agent's docs before assuming a server will show up the same way." } }
+
+ ]
+}
+</script>
+
+
+<script>
+ // Anonymous blog analytics (PostHog) — same posture as the main site and the
+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only
+ // (person_profiles 'never'), no autocapture/recording, DNT respected.
+ (function () {
+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';
+ if (!PH_KEY || navigator.doNotTrack === '1') return;
+ var s = document.createElement('script');
+ s.async = true;
+ s.src = 'https://us-assets.i.posthog.com/static/array.js';
+ s.onload = function () {
+ if (!window.posthog) return;
+ window.posthog.init(PH_KEY, {
+ api_host: 'https://us.i.posthog.com',
+ person_profiles: 'never',
+ autocapture: false,
+ before_send: function (event) {
+ // PostHog fills $ip from the connection unless the event carries one.
+ // Null it here and disable the GeoIP lookup so no IP, city, postal
+ // code or lat/long is ever derived or stored for this page view.
+ if (event && event.properties) {
+ event.properties.$ip = null;
+ event.properties.$geoip_disable = true;
+ }
+ return event;
+ },
+ disable_session_recording: true,
+ respect_dnt: true
+ });
+ };
+ document.head.appendChild(s);
+ })();
+</script>
+</head>
+<body class="theme-press">
+<a class="skip-link" href="#main">Skip to content</a>
+<nav id="nav">
+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
+ </a>
+ <span class="spacer"></span>
+ <div class="links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in">↗ Product</a>
+ </div>
+ <div class="nav-actions">
+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>
+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>
+ </div>
+</nav>
+
+<main id="main">
+
+<article class="t-concepts">
+ <header class="post-head wrap">
+ <nav class="crumbs" aria-label="Breadcrumb">
+ <a href="/blog/">Blog</a>
+ <span>/</span>
+ <a href="/blog/topics/concepts/">Concepts</a>
+ </nav>
+ <h1>What Is an MCP Server?</h1>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
+ <div class="byline">
+ <span class="av" aria-hidden="true">MD</span>
+ <strong>Chaitanya Giri</strong>
+ <span class="dot" aria-hidden="true">·</span>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
+ <span class="dot" aria-hidden="true">·</span>
+ <span>5 min read</span>
+ <span class="tag kind">Concepts</span>
+ </div>
+ </header>
+
+ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="Illustration: What Is an MCP Server?" loading="lazy" decoding="async" /></figure></div>
+
+ <div class="post-wrap wrap">
+ <div class="prose">
+ <div class="callout tldr"><span class="ic">TL;DR</span><p>An <strong>MCP server</strong> is a small program that hands an AI agent tools, data or prompt templates over the <strong>Model Context Protocol</strong>, an open standard. The agent's app (the <strong>host</strong>) opens a <strong>client</strong> connection to each server it uses, the two talk in JSON-RPC over stdio or Streamable HTTP, and the server answers with whatever it was built to expose. One server, many hosts, no custom glue code.</p></div>
+<p>An MCP server is a small program that gives an AI agent access to something it doesn’t have built in: a database, an issue tracker, a browser, your files. It speaks the Model Context Protocol, an open standard, so any compliant AI application can connect the same way, without custom code to wire each one up.</p>
+<p>If you already use one AI coding CLI, this layer matters more once you run several agents at once in a <a href="/blog/what-is-a-multi-agent-harness/">multi-agent harness</a>, because each agent reaches its databases and issue trackers through the servers it has been given, and which agent gets which server becomes your call.</p>
+<h2 id="what-is-an-mcp-server" tabindex="-1">What is an MCP server? <a class="anchor" href="#what-is-an-mcp-server" aria-hidden="true">#</a></h2>
+<p>It’s a program that exposes tools, data or prompt templates to an AI application over the Model Context Protocol. The protocol’s own site describes it as an open standard for connecting AI applications to external systems (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro">modelcontextprotocol.io</a>). Anthropic open sourced MCP on 25 November 2024 (checked 11 Sep 2026, <a href="https://www.anthropic.com/news/model-context-protocol">Introducing the Model Context Protocol</a>), and it’s grown well past Anthropic’s own tools since: the protocol’s own site names ChatGPT, Visual Studio Code and Cursor among the applications that support it.</p>
+<p>The official framing is a USB-C port for AI applications: one connector shape instead of a different adapter for every device. It’s a fair comparison, and a relief if you remember the drawer full of proprietary chargers that preceded USB-C.</p>
+<figure class="fig fig-inline"><img src="/blog/assets/media/what-is-an-mcp-server/note-1.png" alt="Hand-drawn sketch from “What Is an MCP Server?”" loading="lazy" decoding="async" /></figure>
+<h2 id="how-does-an-mcp-server-work" tabindex="-1">How does an MCP server work? <a class="anchor" href="#how-does-an-mcp-server-work" aria-hidden="true">#</a></h2>
+<p>Three roles do the work: a host, a client and a server. The <strong>host</strong> is the AI application, Claude Code or Claude Desktop, say. It opens one <strong>client</strong> for every server it connects to, and each client keeps a dedicated connection to its server (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture">MCP architecture</a>). Client and server exchange JSON-RPC 2.0 messages, and the spec says MCP takes some inspiration from the Language Server Protocol that editors use for programming languages (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/specification/2026-07-28">MCP specification</a>). Those messages travel over one of two transports: stdio for a server running as a local process, or Streamable HTTP for one running remotely, which typically serves many clients at once.</p>
+<p>A client can ask a server which protocol versions and features it supports with one <code>server/discover</code> request, then fetch the actual tools, resources and prompts with <code>tools/list</code>, <code>resources/list</code> and <code>prompts/list</code>, and those lists can change while you work (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture">MCP architecture</a>).</p>
+<h2 id="what-does-an-mcp-server-actually-give-an-agent" tabindex="-1">What does an MCP server actually give an agent? <a class="anchor" href="#what-does-an-mcp-server-actually-give-an-agent" aria-hidden="true">#</a></h2>
+<p>Three things, formally called primitives: tools, resources and prompts. <strong>Tools</strong> are functions the agent can call to do something, like running a query or filing a ticket. <strong>Resources</strong> are data the agent can read for context, like a file’s contents or a database record. <strong>Prompts</strong> are ready made templates the user picks, often shown as slash commands (<a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/server-concepts">MCP server concepts</a>), so a server can ship its own few-shot examples alongside its tools (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture">MCP architecture</a>).</p>
+<p>Claude Code is one MCP host among several, and not every host handles all three: client and server each declare what they support, so check your client’s docs (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture">MCP architecture</a>). Here’s the Claude Code command that manages those servers from the client side, checked on 11 Sep 2026:</p>
+<pre class="language-bash"><code class="language-bash">$ claude <span class="token parameter variable">--version</span>
+<span class="token number">2.1</span>.268 <span class="token punctuation">(</span>Claude Code<span class="token punctuation">)</span>
+
+$ claude mcp <span class="token parameter variable">--help</span>
+Usage: claude mcp <span class="token punctuation">[</span>options<span class="token punctuation">]</span> <span class="token punctuation">[</span>command<span class="token punctuation">]</span>
+
+Configure and manage MCP servers
+
+Options:
+ -h, <span class="token parameter variable">--help</span> Display <span class="token builtin class-name">help</span> <span class="token keyword">for</span> <span class="token builtin class-name">command</span>
+
+Commands:
+ <span class="token function">add</span> <span class="token punctuation">[</span>options<span class="token punctuation">]</span> <span class="token operator">&lt;</span>name<span class="token operator">></span> <span class="token operator">&lt;</span>commandOrUrl<span class="token operator">></span> <span class="token punctuation">[</span>args<span class="token punctuation">..</span>.<span class="token punctuation">]</span> Add an MCP server to Claude Code.
+ <span class="token punctuation">..</span>.
+ list List configured MCP servers. Unapproved
+ .mcp.json servers are shown as ⏸ Pending
+ approval and not connected to<span class="token punctuation">;</span> approved
+ servers are health-checked unless
+ disabled <span class="token keyword">for</span> this project.
+ <span class="token punctuation">..</span>.
+ remove <span class="token punctuation">[</span>options<span class="token punctuation">]</span> <span class="token operator">&lt;</span>name<span class="token operator">></span> Remove an MCP server
+ <span class="token punctuation">..</span>.
+ serve <span class="token punctuation">[</span>options<span class="token punctuation">]</span> Start the Claude Code MCP server</code></pre>
+<p>The full help screen lists eleven subcommands and <code>add</code>’s own usage examples; this excerpt cuts to what matters here (the <code>...</code> lines mark where). <code>add</code> is the client side, wiring a server in; <code>list</code> shows what’s configured and health-checks the approved servers; <code>serve</code> runs Claude Code itself as a server, the same binary on both ends of the protocol. For the actual walkthrough, <a href="/blog/how-to-add-an-mcp-server-to-claude-code/">adding an MCP server to Claude Code</a> covers the scope flag, the <code>.mcp.json</code> file it writes and how to pass an API key.</p>
+<figure class="fig fig-inline"><img src="/blog/assets/media/what-is-an-mcp-server/note-2.png" alt="Hand-drawn sketch from “What Is an MCP Server?”" loading="lazy" decoding="async" /></figure>
+<h2 id="what-is-the-difference-between-an-mcp-server-and-an-api" tabindex="-1">What is the difference between an MCP server and an API? <a class="anchor" href="#what-is-the-difference-between-an-mcp-server-and-an-api" aria-hidden="true">#</a></h2>
+<p>An API is a fixed contract you integrate against by reading its docs and writing client code once, for that one API. An MCP server lists its own tools for any client that asks, in a shape every MCP host already understands, so the same server plugs into Claude Code, an IDE or a chat app with no per app glue. Underneath, many MCP servers wrap an existing API; MCP is the layer that makes the tool discoverable and callable by a model without you writing that translation each time.</p>
+<h2 id="does-an-mcp-server-run-locally-or-does-it-need-the-internet" tabindex="-1">Does an MCP server run locally, or does it need the internet? <a class="anchor" href="#does-an-mcp-server-run-locally-or-does-it-need-the-internet" aria-hidden="true">#</a></h2>
+<p>Either, and the choice belongs to the server, not the protocol. A local server using the stdio transport runs on your own machine, commonly one client at a time, with no network hop at all, which is how the filesystem or a local database server usually ships. A remote server using Streamable HTTP runs on someone else’s infrastructure and can serve many clients at once, the way a hosted issue tracker or CRM server would (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture">MCP architecture</a>).</p>
+<p>Whichever way a server runs, the spec says descriptions of tool behavior “should be considered untrusted, unless obtained from a trusted server” (checked 11 Sep 2026, <a href="https://modelcontextprotocol.io/specification/2026-07-28">MCP specification</a>). That’s exactly the opening <a href="/blog/mcp-security-tool-poisoning/">MCP’s known attacks</a> work through, so approve a server because you’ve read what it does, not on reflex.</p>
+<p>In Munder Difflin 0.5.2, Pro’s Capabilities screen gives each server an on or off switch per Claude Code agent, and a server rated write or secret stays off until you turn it on yourself. The grant reaches Claude Code agents only, so Codex and the other CLIs on the floor don’t get servers from it. MCP itself doesn’t need Munder Difflin: <code>claude mcp add</code> is Claude Code’s own command, and MCP is an open standard either way. <a href="https://munderdiffl.in/download">Download Munder Difflin</a> for the free classic office, or see <a href="https://munderdiffl.in/#pricing">what Pro adds</a> for per-agent control over servers like these.</p>
+
+
+
+ <section class="faq" aria-label="Frequently asked questions">
+ <h2 id="faq">FAQ</h2>
+
+ <div class="qa">
+ <p class="q">What does MCP stand for?</p>
+ <p class="a">Model Context Protocol, the open standard an AI application uses to reach tools, data and prompt templates it does not have built in. Anthropic open sourced it on 25 November 2024, and the specification you would read today is dated 2026-07-28.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Why use an MCP server instead of a plain API?</p>
+ <p class="a">A plain API needs its own client code written by hand for every application that wants to call it. An MCP server lists its own tools when a client asks, in a shape any MCP host already understands, so the same server works in Claude Code, an IDE or a chat app without custom glue for each one.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Can an MCP server access the internet?</p>
+ <p class="a">Yes, if its own code does. An MCP server is an ordinary program, local or remote, and either kind can read files, run commands or call whatever APIs it is written to call. The protocol does not limit what a server can do, only how it talks to the client.</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">What is an MCP server in Claude?</p>
+ <p class="a">The same thing as anywhere else: a program that gives Claude tools, data or prompts over MCP. Claude Code and Claude Desktop can run a local server on your machine, while a custom connector on claude.ai has to be a remote server reached over HTTP. Anthropic&#39;s connector docs also list MCP features Claude does not support yet, such as resource subscriptions, and set a different tool result limit for claude.ai than for Claude Code, so a server can behave differently from one Claude surface to the next (checked 11 Sep 2026, claude.com/docs/connectors/building).</p>
+ </div>
+
+ <div class="qa">
+ <p class="q">Does every AI coding agent support MCP servers?</p>
+ <p class="a">Many do. The protocol&#39;s own site names Claude, ChatGPT, Visual Studio Code and Cursor among the applications that support it, and its architecture page names Claude Code as an example host (checked 11 Sep 2026, modelcontextprotocol.io). Support for each feature and the setup screen still vary, so check a given agent&#39;s docs before assuming a server will show up the same way.</p>
+ </div>
+
+ </section>
+
+
+
+ <hr />
+ <div class="share">
+ <span class="lbl">Tags</span>
+ <a class="tag" href="/blog/tags/concepts/">Concepts</a><a class="tag" href="/blog/tags/mcp/">MCP</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/getting-started/">Getting Started</a>
+ </div>
+
+ </div>
+
+
+ <aside class="toc-rail" aria-label="Table of contents">
+ <div class="tt">On this page</div>
+ <ol>
+ <li class="lvl-2"><a href="#what-is-an-mcp-server">What is an MCP server?</a></li><li class="lvl-2"><a href="#how-does-an-mcp-server-work">How does an MCP server work?</a></li><li class="lvl-2"><a href="#what-does-an-mcp-server-actually-give-an-agent">What does an MCP server actually give an agent?</a></li><li class="lvl-2"><a href="#what-is-the-difference-between-an-mcp-server-and-an-api">What is the difference between an MCP server and an API?</a></li><li class="lvl-2"><a href="#does-an-mcp-server-run-locally-or-does-it-need-the-internet">Does an MCP server run locally, or does it need the internet?</a></li>
+ </ol>
+ </aside>
+
+ </div>
+
+ <footer class="post-foot wrap"><div class="prevnext">
+ <a class="pn prev" href="/blog/codex-cli-vs-claude-code/"><span class="k">← Older</span><span class="t">Codex CLI vs Claude Code</span></a>
+ <a class="pn next" href="/blog/how-to-use-claude-code-plan-mode/"><span class="k">Newer →</span><span class="t">How to Use Claude Code Plan Mode</span></a>
+ </div>
+ <section class="related">
+ <h2>Related in Concepts</h2>
+ <div class="post-grid">
+ <article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-09-10">Sep 10, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>5 min</span>
+ </div>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-07-03">Jul 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>6 min</span>
+ </div>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ </div>
+ </div>
+</article>
+<article class="card t-concepts">
+ <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <div class="body">
+ <div class="meta">
+ <time datetime="2026-07-03">Jul 3, 2026</time>
+ <span class="dot" aria-hidden="true"></span>
+ <span>4 min</span>
+ </div>
+ <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
+ <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <div class="foot">
+ <span class="tag kind">Concepts</span>
+ <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ </div>
+ </div>
+</article>
+
+ </div>
+ </section>
+
+ </footer>
+</article>
+
+</main>
+<footer class="site-foot">
+ <div class="wrap">
+ <div class="foot-top">
+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">
+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />
+ </a>
+ <div class="foot-links">
+ <a href="/blog/">Latest</a>
+ <a href="/blog/topics/">Topics</a>
+ <a href="/blog/about/">About</a>
+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>
+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>
+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>
+ </div>
+ </div>
+ <div class="foot-meta">
+ © 2026 Munder Difflin · Local-first · MIT-licensed ·
+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js &amp; node-pty</a>.
+ Run an office of agents while you sleep.
+ </div>
+ </div>
+</footer>
+
+<script>
+ // sticky-nav border on scroll
+ (function () {
+ var nav = document.getElementById('nav');
+ if (!nav) return;
+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };
+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });
+ })();
+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe
+ (function () {
+ document.addEventListener('click', function (e) {
+ var btn = e.target.closest('.yt-load');
+ if (!btn) return;
+ var box = btn.closest('.yt');
+ var id = box && box.getAttribute('data-yt');
+ if (!id) return;
+ var frame = document.createElement('iframe');
+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';
+ frame.title = box.getAttribute('data-title') || 'YouTube video';
+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';
+ frame.setAttribute('allowfullscreen', '');
+ box.replaceChildren(frame);
+ });
+ })();
+</script>
+
+</body>
+</html>
diff --git a/docs/blog/what-is-harness-engineering/index.html b/docs/blog/what-is-harness-engineering/index.html
index dabb01a8..e06b14c4 100644
--- a/docs/blog/what-is-harness-engineering/index.html
+++ b/docs/blog/what-is-harness-engineering/index.html
@@ -269,50 +269,50 @@
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/whats-new-in-agentic-ai-june-2026/index.html b/docs/blog/whats-new-in-agentic-ai-june-2026/index.html
index c28ec404..d0158869 100644
--- a/docs/blog/whats-new-in-agentic-ai-june-2026/index.html
+++ b/docs/blog/whats-new-in-agentic-ai-june-2026/index.html
@@ -364,50 +364,50 @@ hive run; it’s free and open source.</p>
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/when-do-agents-need-an-agent-protocol/index.html b/docs/blog/when-do-agents-need-an-agent-protocol/index.html
index a9d6e514..41a5f80d 100644
--- a/docs/blog/when-do-agents-need-an-agent-protocol/index.html
+++ b/docs/blog/when-do-agents-need-an-agent-protocol/index.html
@@ -313,50 +313,50 @@ of agents without protocol ceremony; it’s free and open source.</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/why-cli-agents-are-powerful/index.html b/docs/blog/why-cli-agents-are-powerful/index.html
index c9deb16e..2dbed3f6 100644
--- a/docs/blog/why-cli-agents-are-powerful/index.html
+++ b/docs/blog/why-cli-agents-are-powerful/index.html
@@ -351,50 +351,50 @@ capability routing (right agent, not the priciest one).</p>
<h2>Related in Concepts</h2>
<div class="post-grid">
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
- <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
+ <h3><a href="/blog/what-is-an-mcp-server/">What Is an MCP Server?</a></h3>
+ <p class="dek">An MCP server gives an AI agent tools, data and prompts over one open protocol. What it is, the host, client and server roles, and where Claude Code plugs in.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
+ <a class="more" href="/blog/what-is-an-mcp-server/" aria-label="Read: What Is an MCP Server?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>6 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
- <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
+ <h3><a href="/blog/how-much-does-claude-code-cost/">How Much Does Claude Code Cost?</a></h3>
+ <p class="dek">What Claude Code actually costs: free plan access, Claude Pro and Max pricing, per token API rates, and what running several agents does to the bill.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
+ <a class="more" href="/blog/how-much-does-claude-code-cost/" aria-label="Read: How Much Does Claude Code Cost?">Read →</a>
</div>
</div>
</article>
<article class="card t-concepts">
- <a class="thumb t-concepts" href="/blog/review-agent-work-where-it-happens/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/review-agent-work-where-it-happens/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-concepts" href="/blog/loop-engineering-for-ai-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/loop-engineering-for-ai-agents/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>6 min</span>
</div>
- <h3><a href="/blog/review-agent-work-where-it-happens/">Review Agent Work Where It Happens</a></h3>
- <p class="dek">AI agents produce diffs faster than humans can review them, and alt-tabbing to an external editor breaks supervision flow. The case for review-in-place: Munder Difflin&#39;s built-in Monaco IDE puts a CHANGES rail and side-by-side diffs vs HEAD right on the office floor.</p>
+ <h3><a href="/blog/loop-engineering-for-ai-agents/">Loop Engineering: Designing Agent Loops That Converge</a></h3>
+ <p class="dek">Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.</p>
<div class="foot">
<span class="tag kind">Concepts</span>
- <a class="more" href="/blog/review-agent-work-where-it-happens/" aria-label="Read: Review Agent Work Where It Happens">Read →</a>
+ <a class="more" href="/blog/loop-engineering-for-ai-agents/" aria-label="Read: Loop Engineering: Designing Agent Loops That Converge">Read →</a>
</div>
</div>
</article>
diff --git a/docs/blog/your-first-hour-with-munder-difflin/index.html b/docs/blog/your-first-hour-with-munder-difflin/index.html
index de520145..b0efa985 100644
--- a/docs/blog/your-first-hour-with-munder-difflin/index.html
+++ b/docs/blog/your-first-hour-with-munder-difflin/index.html
@@ -326,50 +326,50 @@ schedule. That is the whole distance from “a CLI in a terminal” to “an off
<h2>Related in Guides</h2>
<div class="post-grid">
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-09-10">Sep 10, 2026</time>
+ <time datetime="2026-09-11">Sep 11, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>5 min</span>
</div>
- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>
+ <p class="dek">How Claude Code&#39;s plan mode works: turning it on, what it blocks, real headless --permission-mode plan output, and how to leave it.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
- <time datetime="2026-07-03">Jul 3, 2026</time>
+ <time datetime="2026-09-10">Sep 10, 2026</time>
<span class="dot" aria-hidden="true"></span>
- <span>4 min</span>
+ <span>5 min</span>
</div>
- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
- <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>
+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin&#39;s Capabilities screen grants an MCP server to one agent at a time.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>
</div>
</div>
</article>
<article class="card t-guides">
- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>
+ <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>
<div class="body">
<div class="meta">
<time datetime="2026-07-03">Jul 3, 2026</time>
<span class="dot" aria-hidden="true"></span>
<span>4 min</span>
</div>
- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>
- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can&#39;t do.</p>
+ <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>
+ <p class="dek">A guide to Munder Difflin&#39;s Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent&#39;s budget, and when to watch the board instead of the floor.</p>
<div class="foot">
<span class="tag kind">Guides</span>
- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>
+ <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>
</div>
</div>
</article>
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index f4bfcf66..b587b9db 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -10,7 +10,7 @@
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://munderdiffl.in/</loc>
- <lastmod>2026-09-10</lastmod>
+ <lastmod>2026-09-11</lastmod>
<changefreq>weekly</changefreq>
<priority>1.0</priority>
</url>
@@ -20,6 +20,18 @@
<url><loc>https://munderdiffl.in/blog/</loc><changefreq>daily</changefreq><priority>0.9</priority></url>
<url><loc>https://munderdiffl.in/blog/topics/</loc><changefreq>weekly</changefreq><priority>0.6</priority></url>
<url><loc>https://munderdiffl.in/blog/about/</loc><changefreq>monthly</changefreq><priority>0.4</priority></url>
+ <url>
+ <loc>https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/</loc>
+ <lastmod>2026-09-11</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
+ <url>
+ <loc>https://munderdiffl.in/blog/what-is-an-mcp-server/</loc>
+ <lastmod>2026-09-11</lastmod>
+ <changefreq>monthly</changefreq>
+ <priority>0.8</priority>
+ </url>
<url>
<loc>https://munderdiffl.in/blog/codex-cli-vs-claude-code/</loc>
<lastmod>2026-09-10</lastmod>
@@ -848,22 +860,22 @@
<url><loc>https://munderdiffl.in/blog/tags/story/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/release/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/local-first/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/use-cases/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/tools/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/cost/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/memory/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/workflow/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/human-in-the-loop/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/workflow/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/security/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/mempalace/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
+ <url><loc>https://munderdiffl.in/blog/tags/mcp/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/hive/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/observability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/guardrails/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/electron/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
- <url><loc>https://munderdiffl.in/blog/tags/mcp/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/autonomous/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/git/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>
<url><loc>https://munderdiffl.in/blog/tags/architecture/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>