Skip to content

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

docs(web): focus workflow guide on built-in features

YeonGyu-Kim37d018d8e85c
diff --git a/README.md b/README.md
index 82d6ca0d..417accbc 100644
--- a/README.md
+++ b/README.md
@@ -52,58 +52,51 @@ LazyCodex installs these as OmO commands for Codex. Invoke them with the
Full documentation lives at [lazycodex.ai/docs](https://lazycodex.ai/docs).
-## Build games with LazyCodex
+## Use the built-in workflows
-The first time, there was no grand theory. It worked, so we kept using it.
-After working around a KartRider Drift codebase on [oba.run](https://oba.run),
-the pattern became clear: game projects are where LazyCodex makes the most
-sense.
+LazyCodex should be judged by the features it actually installs. It is a thin
+Codex distribution for OmO: project memory, planning, execution, verified
+completion, skills, hooks, model routing, and diagnostics.
-### 1. `/init-deep` is the map
+### 1. `/init-deep` creates project memory
-Game projects rarely fit a clean folder story. Big repos carry gameplay code,
-tools, editors, content pipelines, experiments, vendor drops, and old milestone
-work in the same tree. The goal is not to make the structure look pure before an
-agent can help. The goal is to give the agent landmarks.
+`/init-deep` generates hierarchical `AGENTS.md` context. It scores complex
+directories, writes local guidance near the code that needs it, and gives future
+agents landmarks before they edit.
-`/init-deep` builds that map by generating hierarchical `AGENTS.md` context. It
-scores complex directories, writes local guidance near the code that needs it,
-and lets future agents find the right files faster.
+Use it when the repository is too large to explain from memory. Run it again
+when the shape of the codebase changes.
-### 2. A game MVP is usually not the product
+### 2. The three command pillars stay up front
-A POC can prove the loop. The product around it is usually several applications:
-Tools, data, launchers, editors, and build pipelines. If the agent only looks at
-the game executable, it misses the actual development system.
+Use `$ulw-plan` when the work needs decisions before implementation. It writes a
+plan to `plans/<slug>.md` and does not touch product code.
-LazyCodex keeps that wider context in play. Use `$ulw-plan` when the shape is
-still fuzzy, `$start-work` when the plan is ready, and `$ulw-loop` when you want
-the agent to keep moving until the evidence says it is done.
+Use `$start-work` when a plan is ready. It executes the checklist with durable
+Boulder progress and stops only when the plan is complete.
-### 3. Dense domains get faster with memory
+Use `$ulw-loop` when the task should keep moving until the result is verified by
+evidence instead of a hopeful status update.
-`/init-deep` is not only a first-run setup command. Rerun it when the milestone changes.
-Run it again when the repo shape changes or when a new subsystem becomes important.
-The result behaves like compressed project memory.
+### 3. Skills cover specialized work
-In legacy game code, the hard part is not reading everything. The hard part is
-knowing where to read first. That is where LazyCodex is strong.
+The command layer stays simple. The skill layer adds specialist judgment for the
+actual work:
-### Skill-first workflows
-
-The three main commands stay simple, but the skill layer is where specialized
-work gets sharper:
-
-| Use case | Reach for |
+| Feature | Use it for |
| --- | --- |
-| Map a messy game repo | `/init-deep` |
-| Turn vague production work into a plan | `$ulw-plan` |
-| Execute a plan with durable progress | `$start-work` |
-| Keep pushing until verified completion | `$ulw-loop` |
-| Review implementation from multiple angles | `review-work` |
-| Remove AI-looking code without changing behavior | `remove-ai-slops` |
-| Build polished UI surfaces | `frontend-ui-ux` |
-| Work safely in strict TypeScript, Rust, Python, or Go | `programming` |
+| `/init-deep` | Hierarchical project memory through `AGENTS.md` |
+| `$ulw-plan` | Decision-complete planning before code changes |
+| `$start-work` | Durable plan execution with Boulder progress |
+| `$ulw-loop` | Verified completion for open-ended tasks |
+| `review-work` | Multi-angle post-implementation review |
+| `remove-ai-slops` | Behavior-preserving cleanup of AI-looking code |
+| `frontend-ui-ux` | Polished UI surfaces |
+| `programming` | Strict TypeScript, Rust, Python, or Go discipline |
+| `LSP` | Diagnostics, definitions, references, symbols, and renames |
+| `AST-grep` | Structural search and rewrite across code |
+| `rules` | Project instructions from AGENTS, rules, and instruction files |
+| `comment-checker` | Feedback after edit-like operations |
Start at [https://lazycodex.ai](https://lazycodex.ai).
diff --git a/packages/web/DESIGN.md b/packages/web/DESIGN.md
index 7f9d8404..871a7a2b 100644
--- a/packages/web/DESIGN.md
+++ b/packages/web/DESIGN.md
@@ -80,11 +80,11 @@ The landing page is a single scrollable document with the following sections, to
- `$start-work` — plan executor
- Each card has a monospace command header, a one-line description, and a syntax example
-5. **Game development + skills guide**
+5. **Built-in workflows + skill coverage**
- The existing three command cards remain the main pillars and appear before this guide
- - Adds "Build games with LazyCodex" positioning for large repos with gameplay, tools, data, launchers, editors, and build pipelines
- - Calls out `/init-deep` as the map for messy project structure
- - Lists skill-first workflows such as `review-work`, `remove-ai-slops`, `frontend-ui-ux`, `programming`, LSP, AST-grep, rules, and comment-checker
+ - Explains the installed LazyCodex workflows: `/init-deep`, `$ulw-plan`, `$start-work`, and `$ulw-loop`
+ - Calls out project memory, planning, execution, and verified completion
+ - Lists built-in skill coverage such as `review-work`, `remove-ai-slops`, `frontend-ui-ux`, `programming`, LSP, AST-grep, rules, and comment-checker
6. **Ultrawork explainer**
- Short paragraph on what `ultrawork` means (OmO discipline mode, parallel agents, auto-verification)
diff --git a/packages/web/app/docs/page.tsx b/packages/web/app/docs/page.tsx
index e9354382..b03edc4e 100644
--- a/packages/web/app/docs/page.tsx
+++ b/packages/web/app/docs/page.tsx
@@ -9,7 +9,7 @@ import "@/app/styles/docs.css";
export const metadata: Metadata = {
title: "Documentation",
description:
- "LazyCodex documentation — install, game-development workflows, skills, ultrawork mode, $ulw-loop, $ulw-plan, $start-work.",
+ "LazyCodex documentation — install, built-in workflows, skills, ultrawork mode, $ulw-loop, $ulw-plan, $start-work.",
alternates: {
canonical: "/docs",
},
@@ -28,7 +28,7 @@ export default function DocsPage() {
<div className="docs-hero">
<h1 className="docs-hero-title">Documentation</h1>
<p className="docs-hero-tagline">
- Learn how to install, configure, and use LazyCodex for ultrawork and skill-first workflows.
+ Learn how to install, configure, and use LazyCodex for ultrawork and built-in workflows.
</p>
</div>
<DocsShell sections={sections}>
diff --git a/packages/web/app/page.tsx b/packages/web/app/page.tsx
index 7c68db87..5742aeca 100644
--- a/packages/web/app/page.tsx
+++ b/packages/web/app/page.tsx
@@ -1,7 +1,7 @@
import type { JSX } from "react"
import { CommandCards } from "../components/site/command-cards"
import { DocsCta } from "../components/site/docs-cta"
-import { GameDevSection } from "../components/site/game-dev-section"
+import { FeatureWorkflowsSection } from "../components/site/feature-workflows-section"
import { Hero } from "../components/site/hero"
import { InstallBlock } from "../components/site/install-block"
import { SiteFooter } from "../components/site/site-footer"
@@ -26,7 +26,7 @@ export default function LandingPage(): JSX.Element {
</div>
<InstallBlock />
<CommandCards />
- <GameDevSection />
+ <FeatureWorkflowsSection />
<UltraworkSection />
<DocsCta />
</main>
diff --git a/packages/web/components/site/game-dev-section.tsx b/packages/web/components/site/feature-workflows-section.tsx
similarity index 83%
rename from packages/web/components/site/game-dev-section.tsx
rename to packages/web/components/site/feature-workflows-section.tsx
index 65194bcb..7d87b473 100644
--- a/packages/web/components/site/game-dev-section.tsx
+++ b/packages/web/components/site/feature-workflows-section.tsx
@@ -1,24 +1,24 @@
import type { JSX } from "react"
import { SITE_CONFIG } from "../../lib/site-config"
-export function GameDevSection(): JSX.Element {
+export function FeatureWorkflowsSection(): JSX.Element {
return (
<section className="mx-auto mt-24 w-full max-w-[1200px] px-4 md:mt-32 md:px-8">
<div className="grid gap-8 border-y border-white/10 py-12 md:grid-cols-[minmax(0,0.9fr)_minmax(0,1.1fr)] md:py-16">
<div>
<p className="font-mono text-xs uppercase text-[color:var(--accent-cyan)]">
- {SITE_CONFIG.gameDev.kicker}
+ {SITE_CONFIG.featureWorkflows.kicker}
</p>
<h2 className="mt-4 text-balance text-[clamp(32px,5vw,56px)] font-medium leading-tight text-[color:var(--text-primary)]">
- {SITE_CONFIG.gameDev.title}
+ {SITE_CONFIG.featureWorkflows.title}
</h2>
<p className="mt-6 max-w-[58ch] text-base leading-relaxed text-[color:var(--text-muted)] md:text-lg">
- {SITE_CONFIG.gameDev.intro}
+ {SITE_CONFIG.featureWorkflows.intro}
</p>
</div>
<div className="grid gap-3">
- {SITE_CONFIG.gameDev.points.map((point, index) => (
+ {SITE_CONFIG.featureWorkflows.points.map((point, index) => (
<div
key={point.label}
className="grid gap-4 rounded-lg border border-white/10 bg-white/[0.03] p-5 md:grid-cols-[72px_1fr]"
@@ -42,14 +42,14 @@ export function GameDevSection(): JSX.Element {
<div className="mt-6 grid gap-4 rounded-lg border border-[color:var(--accent-cyan)]/20 bg-[color:var(--accent-cyan)]/5 p-5 md:grid-cols-[0.9fr_1.1fr] md:p-6">
<div>
<h2 className="text-2xl font-medium text-[color:var(--text-primary)]">
- {SITE_CONFIG.skillWorkflow.title}
+ {SITE_CONFIG.builtInSkills.title}
</h2>
<p className="mt-3 text-sm leading-relaxed text-[color:var(--text-muted)]">
- {SITE_CONFIG.skillWorkflow.summary}
+ {SITE_CONFIG.builtInSkills.summary}
</p>
</div>
<ul className="grid grid-cols-2 gap-2 sm:grid-cols-4">
- {SITE_CONFIG.skillWorkflow.skills.map((skill) => (
+ {SITE_CONFIG.builtInSkills.skills.map((skill) => (
<li
key={skill}
className="rounded-md border border-white/10 bg-black/20 px-3 py-2 font-mono text-xs text-[color:var(--text-secondary)]"
diff --git a/packages/web/content/docs/skills.md b/packages/web/content/docs/skills.md
index 0c1d19dc..e80e8263 100644
--- a/packages/web/content/docs/skills.md
+++ b/packages/web/content/docs/skills.md
@@ -1,12 +1,12 @@
-LazyCodex is most useful when the work is bigger than one prompt. Game projects are a good example: the codebase may include gameplay, tools, data, launchers, editors, and build pipelines in one repo.
+LazyCodex is most useful when you use the features it actually installs: project memory, planning, execution, verified completion, skills, hooks, model routing, and diagnostics.
-### Build games with LazyCodex
+### Built-in workflows
Start with `/init-deep` when the repository is too large or too old to explain from memory. It generates hierarchical `AGENTS.md` context so agents can find the right files before they change code.
-Rerun `/init-deep` when milestones change. A new gameplay loop, content tool, asset pipeline, or launcher can change where the important context lives.
+Use `$ulw-plan` when the work needs decisions before implementation, `$start-work` when a plan should be executed, and `$ulw-loop` when you want the agent to keep going until the result is verified.
-### Skill-first workflows
+### Feature coverage
The three command pillars stay simple:
diff --git a/packages/web/e2e/docs.spec.ts b/packages/web/e2e/docs.spec.ts
index cbb08c7e..f6333924 100644
--- a/packages/web/e2e/docs.spec.ts
+++ b/packages/web/e2e/docs.spec.ts
@@ -60,13 +60,13 @@ test.describe("docs page — structure", () => {
).toBeVisible()
})
- test("documents skills and game-development usage", async ({ page }) => {
+ test("documents skills and built-in workflow usage", async ({ page }) => {
await page.goto("/docs")
const body = page.locator("body")
- await expect(body).toContainText("Build games with LazyCodex")
+ await expect(body).toContainText("Built-in workflows")
await expect(body).toContainText("/init-deep")
- await expect(body).toContainText("Skill-first workflows")
+ await expect(body).toContainText("Feature coverage")
await expect(body).toContainText("review-work")
await expect(body).toContainText("remove-ai-slops")
await expect(body).toContainText("frontend-ui-ux")
diff --git a/packages/web/e2e/landing.spec.ts b/packages/web/e2e/landing.spec.ts
index a965d890..78a37d12 100644
--- a/packages/web/e2e/landing.spec.ts
+++ b/packages/web/e2e/landing.spec.ts
@@ -54,18 +54,15 @@ test.describe("landing page — install + commands", () => {
}
})
- test("game-development guidance keeps the three command pillars first", async ({ page }) => {
+ test("feature workflow guidance keeps the three command pillars first", async ({ page }) => {
await page.goto("/")
await expect(page.locator("article h2")).toHaveText(COMMANDS.map((command) => command.name))
- await expect(page.getByText("Build games with LazyCodex", { exact: false })).toBeVisible()
- await expect(page.getByText("/init-deep", { exact: false }).first()).toBeVisible()
- await expect(
- page
- .getByText("Tools, data, launchers, editors, and build pipelines", { exact: false })
- .first(),
- ).toBeVisible()
- await expect(page.getByText("Skill-first workflows", { exact: false }).first()).toBeVisible()
+ await expect(page.getByText("Use the built-in workflows", { exact: false })).toBeVisible()
+ await expect(page.getByText("Project memory", { exact: false }).first()).toBeVisible()
+ await expect(page.getByText("Planning and execution", { exact: false }).first()).toBeVisible()
+ await expect(page.getByText("Verified completion", { exact: false }).first()).toBeVisible()
+ await expect(page.getByText("Built-in skill coverage", { exact: false }).first()).toBeVisible()
})
})
diff --git a/packages/web/lib/docs-content.generated.ts b/packages/web/lib/docs-content.generated.ts
index fbd888f2..3e1b335d 100644
--- a/packages/web/lib/docs-content.generated.ts
+++ b/packages/web/lib/docs-content.generated.ts
@@ -2,7 +2,7 @@
export const DOC_SOURCES: Record<string, string> = {
"overview.md": "<p>LazyCodex is the lazy way to get <a href=\"https://github.com/code-yeongyu/oh-my-openagent\">oh-my-openagent</a> (OmO) up and running inside Codex. Think <a href=\"https://github.com/LazyVim/LazyVim\">LazyVim</a> for <a href=\"https://github.com/folke/lazy.nvim\">lazy.nvim</a>, but for Codex.</p>\n<h3>What you get</h3>\n<p>OmO is a full AI dev team in a harness. It gives you discipline agents (Sisyphus orchestrates Hephaestus, Oracle, and Librarian), parallel execution, multi-model routing, a skills system, hooks and lifecycle, and zero-config defaults. LazyCodex wraps the entire setup so you don&#39;t have to think about it.</p>\n<h3>The one-word workflow</h3>\n<p>You don&#39;t need to ultrathink. Just prompt with <code>{your prompt} ultrawork</code>. One word, and every agent activates.</p>\n<h3>How it fits together</h3>\n<p>LazyCodex is a thin distribution layer. The core engine is <a href=\"https://github.com/code-yeongyu/oh-my-openagent\">OmO</a>. LazyCodex is maintained by <a href=\"https://sisyphuslabs.ai\">Sisyphus Labs</a>.</p>\n<ul>\n<li><a href=\"https://github.com/code-yeongyu/lazycodex\">LazyCodex on GitHub</a></li>\n<li><a href=\"https://github.com/code-yeongyu/oh-my-openagent\">OmO on GitHub</a></li>\n</ul>\n",
"installation.md": "<p>One command gets you running. LazyCodex installs the Codex platform setup for OmO without a global package install.</p>\n<h3>Install</h3>\n<pre><code class=\"language-bash\">npx lazycodex-ai install\n</code></pre>\n<p>This is exactly equivalent to <code>npx --yes --package oh-my-openagent omo install --platform=codex</code>.</p>\n<h3>Autonomous one-liner</h3>\n<pre><code class=\"language-bash\">npx lazycodex-ai install --no-tui --codex-autonomous\n</code></pre>\n<h3>Prerequisites</h3>\n<ul>\n<li><a href=\"https://bun.sh\">Bun</a></li>\n<li>The <a href=\"https://github.com/openai/codex\">OpenAI Codex CLI</a></li>\n</ul>\n<blockquote>\n<p>Do NOT use <code>npm install -g</code> or <code>bun add -g</code>. Always invoke via <code>npx</code>.</p>\n</blockquote>\n<h3>Let an agent do it</h3>\n<p>It is strongly recommended to let an LLM agent run the install and walk the setup for you. The agent handles subscription detection, model selection, and provider auth automatically.</p>\n",
- "skills.md": "<p>LazyCodex is most useful when the work is bigger than one prompt. Game projects are a good example: the codebase may include gameplay, tools, data, launchers, editors, and build pipelines in one repo.</p>\n<h3>Build games with LazyCodex</h3>\n<p>Start with <code>/init-deep</code> when the repository is too large or too old to explain from memory. It generates hierarchical <code>AGENTS.md</code> context so agents can find the right files before they change code.</p>\n<p>Rerun <code>/init-deep</code> when milestones change. A new gameplay loop, content tool, asset pipeline, or launcher can change where the important context lives.</p>\n<h3>Skill-first workflows</h3>\n<p>The three command pillars stay simple:</p>\n<ul>\n<li><code>$ulw-loop</code> keeps moving until verified completion</li>\n<li><code>$ulw-plan</code> turns fuzzy work into a decision-complete plan</li>\n<li><code>$start-work</code> executes a plan with durable Boulder progress</li>\n</ul>\n<p>Skills add specialist judgment around those pillars:</p>\n<table>\n<thead>\n<tr>\n<th>Skill</th>\n<th>Use it for</th>\n</tr>\n</thead>\n<tbody><tr>\n<td><code>review-work</code></td>\n<td>Multi-angle post-implementation review</td>\n</tr>\n<tr>\n<td><code>remove-ai-slops</code></td>\n<td>Behavior-preserving cleanup of AI-looking code</td>\n</tr>\n<tr>\n<td><code>frontend-ui-ux</code></td>\n<td>Designed UI work instead of generic layout filling</td>\n</tr>\n<tr>\n<td><code>programming</code></td>\n<td>Strict TypeScript, Rust, Python, or Go discipline</td>\n</tr>\n<tr>\n<td><code>LSP</code></td>\n<td>Diagnostics, definitions, references, symbols, and renames</td>\n</tr>\n<tr>\n<td><code>AST-grep</code></td>\n<td>Structural search and rewrite across code</td>\n</tr>\n<tr>\n<td><code>rules</code></td>\n<td>Project instructions from AGENTS, rules, and instruction files</td>\n</tr>\n<tr>\n<td><code>comment-checker</code></td>\n<td>Feedback after edit-like operations</td>\n</tr>\n</tbody></table>\n<h3>Where skills live</h3>\n<p>OmO can load skills from project and user locations such as <code>.opencode/skills</code>, <code>~/.config/opencode/skills</code>, <code>.claude/skills</code>, <code>.agents/skills</code>, and <code>~/.agents/skills</code>.</p>\n<p>LazyCodex installs the Codex Light setup with:</p>\n<pre><code class=\"language-bash\">npx lazycodex-ai install\n</code></pre>\n<p>That installer wires the Codex marketplace plugin as <code>omo@sisyphuslabs</code> while keeping the public package alias easy to remember.</p>\n",
+ "skills.md": "<p>LazyCodex is most useful when you use the features it actually installs: project memory, planning, execution, verified completion, skills, hooks, model routing, and diagnostics.</p>\n<h3>Built-in workflows</h3>\n<p>Start with <code>/init-deep</code> when the repository is too large or too old to explain from memory. It generates hierarchical <code>AGENTS.md</code> context so agents can find the right files before they change code.</p>\n<p>Use <code>$ulw-plan</code> when the work needs decisions before implementation, <code>$start-work</code> when a plan should be executed, and <code>$ulw-loop</code> when you want the agent to keep going until the result is verified.</p>\n<h3>Feature coverage</h3>\n<p>The three command pillars stay simple:</p>\n<ul>\n<li><code>$ulw-loop</code> keeps moving until verified completion</li>\n<li><code>$ulw-plan</code> turns fuzzy work into a decision-complete plan</li>\n<li><code>$start-work</code> executes a plan with durable Boulder progress</li>\n</ul>\n<p>Skills add specialist judgment around those pillars:</p>\n<table>\n<thead>\n<tr>\n<th>Skill</th>\n<th>Use it for</th>\n</tr>\n</thead>\n<tbody><tr>\n<td><code>review-work</code></td>\n<td>Multi-angle post-implementation review</td>\n</tr>\n<tr>\n<td><code>remove-ai-slops</code></td>\n<td>Behavior-preserving cleanup of AI-looking code</td>\n</tr>\n<tr>\n<td><code>frontend-ui-ux</code></td>\n<td>Designed UI work instead of generic layout filling</td>\n</tr>\n<tr>\n<td><code>programming</code></td>\n<td>Strict TypeScript, Rust, Python, or Go discipline</td>\n</tr>\n<tr>\n<td><code>LSP</code></td>\n<td>Diagnostics, definitions, references, symbols, and renames</td>\n</tr>\n<tr>\n<td><code>AST-grep</code></td>\n<td>Structural search and rewrite across code</td>\n</tr>\n<tr>\n<td><code>rules</code></td>\n<td>Project instructions from AGENTS, rules, and instruction files</td>\n</tr>\n<tr>\n<td><code>comment-checker</code></td>\n<td>Feedback after edit-like operations</td>\n</tr>\n</tbody></table>\n<h3>Where skills live</h3>\n<p>OmO can load skills from project and user locations such as <code>.opencode/skills</code>, <code>~/.config/opencode/skills</code>, <code>.claude/skills</code>, <code>.agents/skills</code>, and <code>~/.agents/skills</code>.</p>\n<p>LazyCodex installs the Codex Light setup with:</p>\n<pre><code class=\"language-bash\">npx lazycodex-ai install\n</code></pre>\n<p>That installer wires the Codex marketplace plugin as <code>omo@sisyphuslabs</code> while keeping the public package alias easy to remember.</p>\n",
"ultrawork.md": "<p>ultrawork is the headline mode. Typing <code>ultrawork</code> (or the short alias <code>ulw</code>) anywhere in your prompt activates maximum-precision, outcome-first, evidence-driven orchestration.</p>\n<blockquote>\n<p>&quot;One word. Every agent activates. Doesn&#39;t stop until done.&quot;</p>\n</blockquote>\n<h3>Usage</h3>\n<pre><code class=\"language-bash\">ulw add authentication\n</code></pre>\n<h3>What it enforces</h3>\n<ul>\n<li>Strict TDD: RED → GREEN → SURFACE → CLEAN</li>\n<li>At least 3 realistic QA scenarios</li>\n<li>Real manual-QA channels (HTTP call, tmux, browser)</li>\n<li>A binding verification gate that loops until the work is genuinely done</li>\n</ul>\n",
"ulw-loop.md": "<p><code>$ulw-loop</code> is a self-referential development loop that runs until verified completion.</p>\n<h3>How it works</h3>\n<p>The agent works continuously and emits <code>&lt;promise&gt;DONE&lt;/promise&gt;</code> when it believes the task is complete, but that does NOT end the loop. An Oracle must verify the result first. The loop ends only after the system confirms Oracle verified it. If verification fails, it continues with the message: &quot;Oracle verification failed. Continuing ULTRAWORK loop.&quot;</p>\n<h3>Syntax</h3>\n<pre><code class=\"language-bash\">/ulw-loop &quot;task description&quot; [--completion-promise=TEXT] [--strategy=reset|continue]\n</code></pre>\n<h3>Limits</h3>\n<p>The iteration cap is 500 in ultrawork mode (100 in normal mode).</p>\n",
"ulw-plan.md": "<p><code>$ulw-plan</code> is the strategic planning consultant (Prometheus). It turns an idea into a decision-complete work plan. It is a planner, NOT an implementer. When you say &quot;do X&quot; it produces a plan for X and never writes product code.</p>\n<h3>The flow</h3>\n<ol>\n<li>Socratic interview</li>\n<li>Parallel codebase exploration</li>\n<li>Metis gap analysis</li>\n<li>Writes the plan to <code>plans/&lt;slug&gt;.md</code></li>\n<li>Optional Momus high-accuracy review</li>\n</ol>\n<h3>Output</h3>\n<p>Questions, research, and a work plan you can hand to <a href=\"#start-work\"><code>$start-work</code></a>.</p>\n",
diff --git a/packages/web/lib/docs-sections.ts b/packages/web/lib/docs-sections.ts
index ba972540..a02912aa 100644
--- a/packages/web/lib/docs-sections.ts
+++ b/packages/web/lib/docs-sections.ts
@@ -16,7 +16,7 @@ export type DocSection = {
export const DOC_SECTIONS: readonly DocSection[] = [
{ id: "overview", file: "overview.md", title: "Overview" },
{ id: "installation", file: "installation.md", title: "Installation" },
- { id: "skills", file: "skills.md", title: "Skills guide" },
+ { id: "skills", file: "skills.md", title: "Feature coverage" },
{ id: "ultrawork", file: "ultrawork.md", title: "ultrawork mode" },
{ id: "ulw-loop", file: "ulw-loop.md", title: "$ulw-loop" },
{ id: "ulw-plan", file: "ulw-plan.md", title: "$ulw-plan" },
diff --git a/packages/web/lib/site-config.ts b/packages/web/lib/site-config.ts
index 645a4bde..8cc66e34 100644
--- a/packages/web/lib/site-config.ts
+++ b/packages/web/lib/site-config.ts
@@ -20,30 +20,30 @@ export const SITE_CONFIG = {
},
ultraworkTagline: "One word. Every agent activates. Doesn't stop until done.",
ultraworkExample: "ulw add authentication",
- gameDev: {
- kicker: "Field notes for large repos",
- title: "Build games with LazyCodex",
+ featureWorkflows: {
+ kicker: "What LazyCodex installs",
+ title: "Use the built-in workflows",
intro:
- "Game projects rarely fit a clean folder story. LazyCodex gives agents landmarks before they touch gameplay, tools, data, launchers, editors, and build pipelines.",
+ "LazyCodex is a thin Codex distribution for OmO. It installs the command loop, planner, executor, project-memory setup, skills, hooks, model routing, and verification defaults in one pass.",
points: [
{
- label: "/init-deep is the map",
- text: "Generate hierarchical AGENTS.md context when a repo is too large, old, or cross-cutting to explain from memory.",
+ label: "Project memory",
+ text: "/init-deep generates hierarchical AGENTS.md context so future agents start with local guidance instead of guessing.",
},
{
- label: "The MVP is not the product",
- text: "Keep the surrounding apps in scope: Tools, data, launchers, editors, and build pipelines are often where production risk lives.",
+ label: "Planning and execution",
+ text: "$ulw-plan turns fuzzy work into a plan, then $start-work executes that plan with durable Boulder progress.",
},
{
- label: "Rerun it at milestones",
- text: "Rerun it when the milestone changes so the project memory keeps matching the actual shape of the game.",
+ label: "Verified completion",
+ text: "$ulw-loop keeps work moving until the completion promise is backed by evidence instead of a hopeful status update.",
},
],
},
- skillWorkflow: {
- title: "Skill-first workflows",
+ builtInSkills: {
+ title: "Built-in skill coverage",
summary:
- "The three command pillars stay up front. Skills add the specialist guidance for review, cleanup, UI, language discipline, LSP, AST-grep, rules, and comment-checker feedback.",
+ "Skills add specialist guidance for review, cleanup, UI, strict language work, LSP diagnostics, AST-grep rewrites, project rules, and comment-checker feedback.",
skills: ["review-work", "remove-ai-slops", "frontend-ui-ux", "programming", "LSP", "AST-grep", "rules", "comment-checker"],
},
} as const;
diff --git a/test/readme-game-dev-content.test.mjs b/test/readme-feature-workflows-content.test.mjs
similarity index 64%
rename from test/readme-game-dev-content.test.mjs
rename to test/readme-feature-workflows-content.test.mjs
index c340374f..5f7dbf03 100644
--- a/test/readme-game-dev-content.test.mjs
+++ b/test/readme-feature-workflows-content.test.mjs
@@ -5,13 +5,16 @@ import assert from "node:assert/strict"
const README = readFileSync("README.md", "utf8")
const HANGUL_PATTERN = /[\u1100-\u11ff\u3130-\u318f\uac00-\ud7af]/u
-test("README documents game-development workflows without Hangul", () => {
+test("README documents built-in LazyCodex workflows without Hangul", () => {
const requiredSnippets = [
- "Build games with LazyCodex",
+ "Use the built-in workflows",
"/init-deep",
- "Game projects rarely fit a clean folder story",
- "Tools, data, launchers, editors, and build pipelines",
- "Rerun it when the milestone changes",
+ "project memory",
+ "$ulw-plan",
+ "$start-work",
+ "$ulw-loop",
+ "review-work",
+ "remove-ai-slops",
"https://lazycodex.ai",
]