Open source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the files.
JavaScript ai-agentsai-employeeai-employeesantigravityautomationclaude-codeclaude-skillcodexhermes-agentopenclawopencodescheduled-taskssmall-business
Add Muse and Dots to the harness docs
markfulton7f7de9934eb5
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 4d4d46e..2559038 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -4,6 +4,7 @@ The repo version tracks the kits. Each employee carries its own `CHANGELOG.md` w## Unreleased+- **Muse and Dots join the harness docs.** `docs/HARNESSES.md` gains a row for each: Muse (Meta's Muse Code and the Muse personal agent) and Dots (OpenAI's always on agents, announced September 29, 2026), with Dots added to the hosted shape section beside Grok Bot. The README strip, the prerequisites, install, FAQ and contributing pages now name thirteen harnesses. The kits themselves are unchanged.- **A Claude Code plugin.** The repository root is now the plugin `ai-employees` and its own marketplace (`.claude-plugin/plugin.json`, `.claude-plugin/marketplace.json`). `/plugin marketplace add markfulton/ai-employees`, then `/plugin install ai-employees@ai-employees`, and `/ai-employees:hire` is available in every session. The plugin carries all eight kits and the installer, so a hire needs no download.- **The `hire` skill, rewritten.** It now runs the bundled installer instead of copying by hand, so a skill hire writes `.installed.json` like an `npx` hire and a later upgrade can tell the member's edits from ours. It adds which employee to hire first, what to check the next weekday, the guardrails, and how a hired employee is directed, corrected, rescheduled and upgraded.diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex 65424a0..7840f97 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -7,7 +7,7 @@ Thank you for looking under the hood. This repo is eight AI employees, each a fo- **Corrections from a real run.** A routine that asked for something it should have researched, a browser flow that no longer matches a site, a rule that reads wrong on a Monday morning. Open an issue with the routine id and what happened, or a pull request with the smallest change that fixes it. From 1.7.0 on your employee drafts these for you: once a month it writes the repairs it made to its own instructions that would help every install to `improvements/contribution-draft-YYYY-MM.md`, with your business taken out. Read it, then paste it into an issue. It never sends anything itself.- **Routine requests.** A routine one of the eight should have. Use the routine request template; say which employee, what it would own, and what it must never do, and answer the five questions in `docs/STANDARD.md` section 4: trigger, frequency, output, silence, stop.- **Employee proposals.** A ninth role. Use the employee request template. Read `docs/HOW-EMPLOYEES-WORK.md` first, because a proposal that keeps the two guardrails and the schedule model is one I can build on.-- **Harness notes.** Ran a kit on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code or DeepSeek, or on a Mac through launchd or Linux through cron? Open an issue with the invocation you used, what the first run record said, and what you changed, and it goes into the notes in `docs/HARNESSES.md` with your name on the change.+- **Harness notes.** Ran a kit on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse or Dots, or on a Mac through launchd or Linux through cron? Open an issue with the invocation you used, what the first run record said, and what you changed, and it goes into the notes in `docs/HARNESSES.md` with your name on the change.- **Show and tell.** Post what an AI Employee did for your business in Discussions under Show and tell. Good builds go into the README with your name on them.## Before you open a pull requestdiff --git a/README.md b/README.mdindex 9bae9fb..1a83ed3 100644--- a/README.md+++ b/README.md@@ -36,7 +36,7 @@</p><p align="center">- <a href="https://club.reinventing.ai/ai-employees?utm_source=github&utm_medium=readme&utm_campaign=ai-employees&utm_content=harness-strip#install"><img src="assets/harness-strip.png" width="838" alt="Runs on the agent you use: Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek"></a>+ <a href="https://club.reinventing.ai/ai-employees?utm_source=github&utm_medium=readme&utm_campaign=ai-employees&utm_content=harness-strip#install"><img src="assets/harness-strip.png" width="838" alt="Runs on the agent you use: Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots"></a></p><p align="center">@@ -83,7 +83,7 @@ This repository is also a Claude Code plugin with one skill, `hire`, and all eigThen say "hire the GTM Engineer into D:\AgentOps\gtm-engineer", or run `/ai-employees:hire`. The skill checks the folder is outside cloud sync, copies the kit from the plugin with no download, runs the self tests, and tells you the one line to say in a fresh session in that folder. It registers nothing and sends nothing. [The plugin page](https://club.reinventing.ai/plugin?utm_source=github&utm_medium=readme&utm_campaign=ai-employees&utm_content=plugin) has the same steps with a walkthrough.-**Not on Claude Code?** The same two steps work on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek. [docs/HARNESSES.md](docs/HARNESSES.md) has the command for each.+**Not on Claude Code?** The same two steps work on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots. [docs/HARNESSES.md](docs/HARNESSES.md) has the command for each.<table><tr><td align="center" width="900">diff --git a/assets/README.md b/assets/README.mdindex 8abff73..31a48d3 100644--- a/assets/README.md+++ b/assets/README.md@@ -12,7 +12,7 @@ The README wordmark is `logo-light.png` and `logo-dark.png`, 1680 by 400 with aThe four header buttons are `btn-install.png`, `btn-join.png`, `btn-sessions.png` and `btn-club.png`, one image each so each keeps its own link and its own `utm_content`. They are 60 tall and as wide as their own text (260, 199, 163 and 186), rendered at three times scale from `src/header-buttons.html` with `#install`, `#join`, `#sessions` or `#club` on the URL and `--window-size=<width>,60`. The club's three colours carry the order of importance: cream for the primary action, signal blue for the second, navy for the two that follow. Every button has a rim, so cream holds on GitHub's light theme and navy on its dark one.-`harness-strip.png` is the compatibility strip in the README header: 838 by 92, rendered at three times scale. It shows the eleven agents in `docs/HARNESSES.md`, in that order, each brand's own favicon on a white tile so a dark mark never disappears into the navy. It renders from `src/harness-strip.html`, which reads the icons from the club repository checked out beside this one (`agent-ops-club/public/img/harnesses`). Rebuild it with `--allow-file-access-from-files --force-device-scale-factor=3 --window-size=838,92`. Adding a harness means adding it to `docs/HARNESSES.md`, to the list in that page, and to the alt text in the README.+`harness-strip.png` is the compatibility strip in the README header: 838 by 92, rendered at three times scale. It shows the thirteen agents in `docs/HARNESSES.md`, in that order, each brand's own favicon on a white tile so a dark mark never disappears into the navy. It renders from `src/harness-strip.html`, which reads the icons from the club repository checked out beside this one (`agent-ops-club/public/img/harnesses`). Rebuild it with `--allow-file-access-from-files --force-device-scale-factor=3 --window-size=838,92`. Adding a harness means adding it to `docs/HARNESSES.md`, to the list in that page, and to the alt text in the README.Three more images live in this folder; the first two and are built from the same eight square thumbnails:diff --git a/assets/harness-strip.png b/assets/harness-strip.pngindex 3689991..251b4ef 100644Binary files a/assets/harness-strip.png and b/assets/harness-strip.png differdiff --git a/assets/src/harness-strip.html b/assets/src/harness-strip.htmlindex ae1f3f3..377135b 100644--- a/assets/src/harness-strip.html+++ b/assets/src/harness-strip.html@@ -1,16 +1,16 @@<!doctype html><html><head><meta charset="utf-8"><link href="https://fonts.googleapis.com/css2?family=Inter:wght@500;600&family=JetBrains+Mono:wght@500&display=swap" rel="stylesheet"><style>-/* The README compatibility strip: the eleven agents in docs/HARNESSES.md, in+/* The README compatibility strip: the thirteen agents in docs/HARNESSES.md, inthat order. A navy card so it reads the same on GitHub's light and darkthemes, and every icon sits on its own white tile so a dark mark neverdisappears into the ground. Icons are each brand's own favicon, the samefiles the club's harness bar uses. */html,body{margin:0;padding:0;background:transparent}.s{position:relative;width:838px;height:92px;box-sizing:border-box;border-radius:14px;overflow:hidden;background:#0D161B;border:1px solid rgba(241,232,203,.14);- display:flex;align-items:center;padding:0 14px 0 22px;font-family:Inter,system-ui,sans-serif}+ display:flex;align-items:center;padding:0 8px 0 18px;font-family:Inter,system-ui,sans-serif}.glow{position:absolute;inset:0;background:radial-gradient(420px 160px at 100% 0%,rgba(11,127,199,.22),transparent 70%)}-.label{position:relative;flex:none;width:88px;font-family:"JetBrains Mono",monospace;font-weight:500;font-size:9.5px;line-height:1.6;letter-spacing:.18em;color:#cfc6ab}+.label{position:relative;flex:none;width:72px;font-family:"JetBrains Mono",monospace;font-weight:500;font-size:9.5px;line-height:1.6;letter-spacing:.18em;color:#cfc6ab}.label b{display:block;color:#f1e8cb;font-weight:500}.rule{position:relative;flex:none;width:1px;height:44px;background:rgba(241,232,203,.16);margin-right:6px}.row{position:relative;flex:1;display:flex;align-items:flex-start}@@ -18,7 +18,7 @@ html,body{margin:0;padding:0;background:transparent}.t{width:34px;height:34px;margin:0 auto;border-radius:9px;background:#fff;display:flex;align-items:center;justify-content:center;overflow:hidden;box-shadow:0 4px 14px rgba(0,0,0,.4)}.t img{width:24px;height:24px;display:block;border-radius:4px}.t.full img{width:34px;height:34px;border-radius:0}-.n{margin-top:7px;font-size:10px;font-weight:600;color:#f1e8cb;white-space:nowrap;letter-spacing:-.01em}+.n{margin-top:7px;font-size:9px;font-weight:600;color:#f1e8cb;white-space:nowrap;letter-spacing:-.01em}</style></head><body><div class="s"><div class="glow"></div><div class="label"><b>RUNS ON</b>THE AGENT<br>YOU USE</div><div class="rule"></div>@@ -26,7 +26,7 @@ html,body{margin:0;padding:0;background:transparent}</div><script>const base="../../../agent-ops-club/public/img/harnesses/";-const list=[["claude-code","Claude Code"],["openclaw","OpenClaw"],["hermes","Hermes"],["opencode","OpenCode"],["grokbot","Grok Bot"],["codex","Codex"],["antigravity","Antigravity"],["pi","Pi"],["cline","Cline"],["qwen-code","Qwen Code"],["deepseek","DeepSeek"]];+const list=[["claude-code","Claude Code"],["openclaw","OpenClaw"],["hermes","Hermes"],["opencode","OpenCode"],["grokbot","Grok Bot"],["codex","Codex"],["antigravity","Antigravity"],["pi","Pi"],["cline","Cline"],["qwen-code","Qwen Code"],["deepseek","DeepSeek"],["muse","Muse"],["dots","Dots"]];const full=new Set(location.hash.slice(1).split(",").filter(Boolean));document.getElementById("row").innerHTML=list.map(([s,n])=>`<div class="h"><div class="t${full.has(s)?" full":""}"><img src="${base}${s}.png"></div><div class="n">${n}</div></div>`).join("");</script>diff --git a/docs/FAQ.md b/docs/FAQ.mdindex 80d88ef..4b25ffc 100644--- a/docs/FAQ.md+++ b/docs/FAQ.md@@ -8,7 +8,7 @@**Windows, macOS or Linux?** All three. Windows through the Desktop app scheduler or Task Scheduler, macOS through the Desktop app or launchd, Linux through cron. `docs/INSTALL.md` has the steps for each scheduler and what a first run should look like.-**Which harness?** Built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek. Claude Code is the one the GTM Engineer runs my own club launch on every weekday. OpenClaw, Hermes, Cline and Qwen Code have built in cron or scheduled tasks, Codex has scheduled runs, Antigravity has the `agy` job runner, DeepSeek schedules through a plugin, OpenCode and Pi use the operating system's scheduler, and Grok Bot runs from its own cloud computer. `docs/HARNESSES.md` has the invocation and the first run check for each.+**Which harness?** Built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots. Claude Code is the one the GTM Engineer runs my own club launch on every weekday. OpenClaw, Hermes, Cline and Qwen Code have built in cron or scheduled tasks, Codex has scheduled runs, Antigravity has the `agy` job runner, DeepSeek schedules through a plugin, OpenCode and Pi use the operating system's scheduler, and Grok Bot, Muse and Dots run from a cloud computer of their own. `docs/HARNESSES.md` has the invocation and the first run check for each.**Does it run on Grok Bot?** Yes, with one difference: the bot's computer is not yours. The bot installs the kit on its own cloud computer, you paste the kit's `AGENTS.md` into the bot's Instructions field, one recurring task per routine runs from `SCHEDULE.md`, and the morning brief is posted into the bot's own thread because you never open that computer's files. Every bot on your account shares that computer and every login on it, so scope by what you sign in to, never by which bot you talk to. The hosted section of `docs/HARNESSES.md` has the detail.diff --git a/docs/HARNESSES.md b/docs/HARNESSES.mdindex 5c48a18..16ea740 100644--- a/docs/HARNESSES.md+++ b/docs/HARNESSES.md@@ -2,7 +2,7 @@Every routine is one `SKILL.md` with `name` and `description` frontmatter, plain markdown instructions, and no clock time in it. Any harness that can read files, write files, run a command, read the clock, and (ideally) drive your signed in browser can run one. What differs is the scheduler and the invocation, and this page has both for each harness, with the one thing to check on a first run.-The kits are built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek, and run on Windows, macOS and Linux. Claude Code on Windows is where the GTM Engineer has run my own club launch every weekday since August 27.+The kits are built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots, and run on Windows, macOS and Linux. Claude Code on Windows is where the GTM Engineer has run my own club launch every weekday since August 27.Two rules hold on every harness. **Routines are scheduled jobs, not skills**: point the scheduler at the kit's `routines/` folder and never copy them into a global skills directory, because a skills directory loads all of them into every session you open and lets any of them be invoked outside its window, where it will only record a skip and exit. **Keep one copy**: every routine ends with a `## Corrections` section you write into and it reads on its next run, and two copies means you write into one and it reads from the other.@@ -23,6 +23,8 @@ Two rules hold on every harness. **Routines are scheduled jobs, not skills**: po| Cline | Ready | Built in cron: `cline schedule create "<prompt>" --cron "<cron>"`, one per routine, auto approve on | The prompt is `Read <root>/routines/<id>/SKILL.md and follow it.` | That a scheduled run starts in the kit folder, and that auto approve is on so it never hangs | `~/.cline/mcp.json`, Streamable HTTP with a token header || Qwen Code | Ready | Built in scheduled tasks, or the operating system's | `qwen -p "<prompt>"`, confirm against `qwen --help` | That it can write inside the kit folder and reach the network | `qwen mcp add <name> <url>`, or `mcpServers` in `~/.qwen/settings.json` || DeepSeek | Ready | Its scheduling plugin, one run per routine | `dsh` runs a local server; confirm the headless prompt form against `dsh --help` | Whether it drives your signed in browser profile or a clean one | Its MCP plugin, one server per plugin row |+| Muse | Ready | Muse Code has loop jobs that stop when the terminal closes, so use the operating system's, one job per routine. Muse, the personal agent, runs crons on its own cloud machine | Muse Code: `muse exec` with approvals disabled and `Read <root>/routines/<id>/SKILL.md and follow it.` as the prompt. Muse: the same prompt as a cron on its cloud machine | Muse Code reads the Claude Code skill format directly and imports existing skills with one command; confirm it with `muse exec` on one routine. For Muse, whether its cloud machine can reach your signed in accounts at all | MCP servers connected in Muse Code; connectors in Muse |+| Dots | Ready | Always on from its own cloud computer, so ask your dot to run each routine on the schedule `SCHEDULE.md` names, one task per routine | You give your dot the kit and each routine's `Read <root>/routines/<id>/SKILL.md and follow it.` as the task, from ChatGPT, Slack or Teams | That the dot keeps the kit folder on its own computer between runs, and can reach the accounts the routine reads. Open its computer and read the first run. Its background research uses read only tools, and sensitive actions such as changing a password always stay with you | Plugins, connected through your ChatGPT app controls, with Custom Rules to allow, require approval for or block specific actions |Every kit's `CAPABILITIES.md` section 4b names the connections that read its accounts without a browser, with the read only form of each route. The column above is how each harness adds one. A kit never installs a connection; the install prompt checks for each and names the absent ones in its handover.@@ -35,12 +37,13 @@ Every kit's `CAPABILITIES.md` section 4b names the connections that read its acc## Grok Bot, and the hosted shape it set-Grok Bot is the one harness on this page whose computer is not yours, and the shape is worth writing down once because Codex cloud and Meta Muse share it. Everything here comes from operators' published accounts of the product in August 2026, and each kit's `CAPABILITIES.md` marks it `expected` until you write `confirmed` into `## Corrections`.+Grok Bot is the one harness on this page whose computer is not yours, and the shape is worth writing down once because Codex cloud, Meta Muse and OpenAI Dots share it. Everything here comes from operators' published accounts of the product in August 2026, and each kit's `CAPABILITIES.md` marks it `expected` until you write `confirmed` into `## Corrections`.- **One computer for every bot.** All the bots on an account share one persistent Linux machine with a terminal, file access and a real browser. Each bot has its own screen and runs one computer-use task at a time; several bots can drive the browser at once. So the kit lives on that computer, the bot installs it there itself, and the cloud sync rule does not apply.- **One bot per Employee, one task per routine.** Name the bot after the role, paste the kit's `AGENTS.md` into its Instructions field (it is the map that points at the files, and it is short enough to fit), and register one recurring task per routine with the Shape B prompt. Do not turn the routines into the bot's workflows: a workflow is invoked on demand, a routine runs in a window.- **Bots are not a security boundary.** Files, browser sessions and app logins are shared by every bot on the computer. A release you write for one Employee is a file every bot can read; a session you sync there is a session every bot can use. Scope by what you sign in to, never by which bot you talk to, and start read only on public pages before you sync anything.- **Staying signed in is a sync you run.** Nothing in a kit signs in, so your sessions reach the bot's browser only if you signed in there or you keep them there with a cookie sync such as Agent Cookie (Chrome cookies from a Mac to the bot over Tailscale, every fifteen minutes). The kit names it under `browser.session`, detects it, and installs nothing.+- **Dots is the same shape inside ChatGPT.** OpenAI announced it on September 29, 2026: each dot has its own cloud computer and browser, is powered by GPT-6 Astra, connects to apps through plugins, and reaches you from ChatGPT, Slack and Teams. It is rolling out to Pro and Business Premium plans in eligible markets, with an Enterprise beta. You can open its computer at any time, which makes the first run easy to inspect. Its Activity View shows background work, and Custom Rules set what it may do without asking.- **The brief comes to your thread.** You never open that computer's files, so the standup resolves `brief.deliver` and posts `brief-latest.md` into the bot's own thread, which the Grok app carries to your phone. The file stays the record.- **Two more routes.** Claude Code can be logged in on the bot's computer, which turns the Grok Bot row into the Claude Code CLI row with Grok Bot as the scheduler. Peekaboo, installed by you on a Mac, lets the bot see and click native Mac apps over the same link. Both are yours to add.- **Watch the meter.** Plans carry a weekly usage allowance and fleet work moves it fast. Start on the lowest tier that includes bots, run one Employee for a week, and read the meter before you add a second.diff --git a/docs/INSTALL.md b/docs/INSTALL.mdindex 941145a..e5dbc4b 100644--- a/docs/INSTALL.md+++ b/docs/INSTALL.md@@ -122,7 +122,7 @@ One line per routine, from `CAPABILITIES.md` section 9.3, with the full path to### The other ten harnesses-OpenClaw, Hermes, Cline and Qwen Code have a built in cron, Codex has scheduled runs, Antigravity has the `agy` job runner, DeepSeek schedules through a plugin, and Grok Bot runs recurring tasks from its own cloud computer: register one job per routine in that scheduler, with the kit folder as the working directory, the fire time from `SCHEDULE.md`, and the prompt `Read <root>/routines/<id>/SKILL.md and follow it.`. OpenCode and Pi have no scheduler of their own, so use the operating system's route above with their headless command in place of `claude -p`. `docs/HARNESSES.md` has the exact invocation and the first run check for each, and the same rule holds everywhere: run one routine by hand before you register the rest. Grok Bot is the one whose computer is not yours: the bot installs the kit on its own cloud computer, you paste the kit's `AGENTS.md` into the bot's Instructions field, and the brief reaches you in the bot's thread. The hosted section of `docs/HARNESSES.md` has the rest, including what the shared computer means for your logins.+OpenClaw, Hermes, Cline and Qwen Code have a built in cron, Codex has scheduled runs, Antigravity has the `agy` job runner, DeepSeek schedules through a plugin, and Grok Bot, Muse and Dots run recurring tasks from a cloud computer of their own: register one job per routine in that scheduler, with the kit folder as the working directory, the fire time from `SCHEDULE.md`, and the prompt `Read <root>/routines/<id>/SKILL.md and follow it.`. OpenCode and Pi have no scheduler of their own, so use the operating system's route above with their headless command in place of `claude -p`. `docs/HARNESSES.md` has the exact invocation and the first run check for each, and the same rule holds everywhere: run one routine by hand before you register the rest. Grok Bot is the one whose computer is not yours, and Muse and Dots share that shape: the bot installs the kit on its own cloud computer, you paste the kit's `AGENTS.md` into the bot's Instructions field, and the brief reaches you in the bot's thread. The hosted section of `docs/HARNESSES.md` has the rest, including what the shared computer means for your logins.## What a first day looks likediff --git a/docs/PREREQUISITES.md b/docs/PREREQUISITES.mdindex 12a4938..f59361a 100644--- a/docs/PREREQUISITES.md+++ b/docs/PREREQUISITES.md@@ -2,13 +2,13 @@Ten things, and one optional eleventh. Every line here was either measured on my own machine or read from the vendor's own page, and the install prompt checks the ones it can. Read this before `npx ai-employees hire` or a clone, because the one thing that fails silently is the login, and it fails after everything else looks fine.-The kits run on eleven harnesses: Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek. Claude Code is the worked example in every item below because it is the one I run these on every weekday. Where another harness differs, the item says so, and `docs/HARNESSES.md` has the scheduler, the invocation and the first run check for each of the eleven.+The kits run on thirteen harnesses: Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots. Claude Code is the worked example in every item below because it is the one I run these on every weekday. Where another harness differs, the item says so, and `docs/HARNESSES.md` has the scheduler, the invocation and the first run check for each of the thirteen.## 1. An agent harness that can do four thingsRead and write files in a folder, read the machine clock and timezone, run a local command, and, for the browser lane, drive a browser that carries your own signed in sessions. Any of the eleven qualifies. Pick the one you already use; nothing in a kit is written for one harness's tools, because the routines name capabilities and `CAPABILITIES.md` in each kit maps them to a route per harness.-On Claude Code that means a plan that includes it: Pro, Max 5x, Max 20x, Team or Enterprise. The free plan does not include Claude Code. An Anthropic Console API key also works, but it turns the browser lane off (item 6), so the routines that read your own accounts fall back to public pages. On the other ten, the account or key the harness already runs on is the whole requirement; the kits add no credential of their own.+On Claude Code that means a plan that includes it: Pro, Max 5x, Max 20x, Team or Enterprise. The free plan does not include Claude Code. An Anthropic Console API key also works, but it turns the browser lane off (item 6), so the routines that read your own accounts fall back to public pages. On the other twelve, the account or key the harness already runs on is the whole requirement; the kits add no credential of their own.## 2. The harness installed, in a shape you can schedule@@ -21,7 +21,7 @@ On Claude Code the two shapes are:Minimums from Claude Code's setup page: macOS 13.0 or later, Windows 10 1809 or later, Ubuntu 20.04 or later, 4 GB of RAM.-On the other ten, install the harness the way its own page says. OpenClaw, Hermes, Cline, Qwen Code, Codex, Antigravity and DeepSeek bring a scheduler; Grok Bot runs its schedule from its own cloud computer; OpenCode and Pi have none of their own and pair with the operating system's. `docs/HARNESSES.md` has one row per harness.+On the other twelve, install the harness the way its own page says. OpenClaw, Hermes, Cline, Qwen Code, Codex, Antigravity and DeepSeek bring a scheduler; Grok Bot, Muse and Dots run their schedules from a cloud computer of their own; OpenCode and Pi have none of their own and pair with the operating system's. `docs/HARNESSES.md` has one row per harness.## 3. Logged in, by a human, once@@ -60,7 +60,7 @@ On Claude Code that means Google Chrome or Microsoft Edge, the Claude in ChromeYour harness's own, where it has one:- The Claude Desktop app's local scheduled tasks (Routines, Local), one task per routine, named after the routine id.-- The built in cron in OpenClaw, Hermes, Cline and Qwen Code; Codex scheduled runs; the Antigravity `agy` job runner; the DeepSeek scheduling plugin; a recurring task per routine on Grok Bot.+- The built in cron in OpenClaw, Hermes, Cline and Qwen Code; Codex scheduled runs; the Antigravity `agy` job runner; the DeepSeek scheduling plugin; a recurring task per routine on Grok Bot, Muse and Dots.Otherwise the operating system's:@@ -88,4 +88,4 @@ Every kit's `CAPABILITIES.md` has a section 4b naming the connections that read## Where it runs-Built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek, and runs on Windows, macOS and Linux. Windows through the Desktop app scheduler or Task Scheduler, macOS through the Desktop app or launchd, Linux through cron, and the harnesses with a scheduler of their own through that. `docs/HARNESSES.md` has the invocation and the first run check for each, and `docs/INSTALL.md` has the steps per operating system.+Built for Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots, and runs on Windows, macOS and Linux. Windows through the Desktop app scheduler or Task Scheduler, macOS through the Desktop app or launchd, Linux through cron, and the harnesses with a scheduler of their own through that. `docs/HARNESSES.md` has the invocation and the first run check for each, and `docs/INSTALL.md` has the steps per operating system.diff --git a/docs/WHAT-SETS-THEM-APART.md b/docs/WHAT-SETS-THEM-APART.mdindex 47096ba..a75bfbb 100644--- a/docs/WHAT-SETS-THEM-APART.md+++ b/docs/WHAT-SETS-THEM-APART.md@@ -5,7 +5,7 @@- **One push to your phone, only when you are the blocker.** A login expired, a credential is missing, your conversion tracking stopped while ads are live, or a run died holding the browser. Four cases and no fifth. One short line, never twice for the same thing, never outside your working hours, never on a first run. Everything else waits for the brief. [The one push](STANDARD.md#23-the-one-push).- **The brief comes to you.** After the standup writes it, the routine brings it to wherever you are: the dashboard on your own machine, the Employee's own thread on a hosted agent such as Grok Bot, or your own inbox where a mail route exists. A brief on a computer you never open is no brief, so on a hosted harness it lands in your thread and the Grok app carries it to your phone.- **They use the connections you already have.** Where your agent already has a connector for an account, the routine reads through it instead of the screen: Meta's own Ads MCP server for an ad account, the Gmail connector for drafts and replies, the Vercel and Supabase connectors for logs and advisors, Metricool for publishing. Each kit names its connections in one table, uses them read only, and works without any of them; nothing is installed for you.-- **They run on the agent you already use.** Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek, without a routine changing by one word. Routines describe what they need done, and one file per kit says how each agent does it.+- **They run on the agent you already use.** Claude Code, OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots, without a routine changing by one word. Routines describe what they need done, and one file per kit says how each agent does it.- **One routine, one job, one output.** Routines run solo and never supervise each other; the Chief of Staff reads their run logs afterwards and names what quietly stopped. Crews of agents that hand work to each other unsupervised have been measured multiplying their own errors many times over, and a wrong step here lands in your brief instead of in three other routines.- **You can direct any of them in chat.** Open a session in the employee's folder and it does anything you could do by hand, on your word: tick a card you confirmed, stage a form now, retune a strategy file, correct a stale brief. It leaves the same trail a routine would, and the scheduled runs treat that work as yours.- **You set how far they go.** Every employee drafts, fills and stages by default, and the last click is yours. Release a channel in `RELEASES.md` and the routine completes that action itself from then on. Your agent's own permission settings are the gate, and every file in the kit is plain text in your own folder, yours to change.diff --git a/skills/hire/SKILL.md b/skills/hire/SKILL.mdindex 9a37267..2b6ff9d 100644--- a/skills/hire/SKILL.md+++ b/skills/hire/SKILL.md@@ -102,7 +102,7 @@ Use this to answer questions after the hire.**Upgrading.** Once a month the brief says when a newer kit is out. `npx ai-employees upgrade <slug> --to "<folder>"` reports what would change, and `--apply` takes it. It never overwrites a file the user edited.-**Other agents.** The same kits run on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code and DeepSeek. `docs/HARNESSES.md` has the command and the scheduler for each.+**Other agents.** The same kits run on OpenClaw, Hermes, OpenCode, Grok Bot, Codex, Antigravity, Pi, Cline, Qwen Code, DeepSeek, Muse and Dots. `docs/HARNESSES.md` has the command and the scheduler for each.## 9. Close