@every-env/compound-plugin 0.3.0 → 0.5.1

package/{plugins/compound-engineering → .claude}/commands/release-docs.md

@@ -2,7 +2,6 @@
 name: release-docs
 description: Build and update the documentation site with current plugin components
 argument-hint: "[optional: --dry-run to preview changes without writing]"
-disable-model-invocation: true
 ---
 
 # Release Documentation Command

package/.claude-plugin/marketplace.json

@@ -11,8 +11,8 @@
   "plugins": [
     {
       "name": "compound-engineering",
-      "description": "AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 29 specialized agents, 24 commands, and 18 skills.",
-      "version": "2.31.0",
+      "description": "AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 29 specialized agents, 22 commands, and 19 skills.",
+      "version": "2.33.0",
       "author": {
         "name": "Kieran Klaassen",
         "url": "https://github.com/kieranklaassen",

package/.github/workflows/ci.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2

package/.github/workflows/deploy-docs.yml

@@ -24,13 +24,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Setup Pages
-        uses: actions/configure-pages@v4
+        uses: actions/configure-pages@v5
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
+        uses: actions/upload-pages-artifact@v4
         with:
           path: 'plugins/compound-engineering/docs'
 

package/.github/workflows/publish.yml

@@ -0,0 +1,37 @@
+name: Publish to npm
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Install dependencies
+        run: bun install
+
+      - name: Run tests
+        run: bun test
+
+      - name: Setup Node.js for npm publish
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          registry-url: "https://registry.npmjs.org"
+
+      - name: Publish to npm
+        run: npm publish --provenance --access public
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}

package/README.md

@@ -12,9 +12,9 @@ A Claude Code plugin marketplace featuring the **Compound Engineering Plugin**
 /plugin install compound-engineering
 ```
 
-## OpenCode + Codex (experimental) Install
+## OpenCode, Codex, Droid & Cursor (experimental) Install
 
-This repo includes a Bun/TypeScript CLI that converts Claude Code plugins to OpenCode and Codex.
+This repo includes a Bun/TypeScript CLI that converts Claude Code plugins to OpenCode, Codex, Factory Droid, and Cursor.
 
 ```bash
 # convert the compound-engineering plugin into OpenCode format
@@ -22,6 +22,12 @@ bunx @every-env/compound-plugin install compound-engineering --to opencode
 
 # convert to Codex format
 bunx @every-env/compound-plugin install compound-engineering --to codex
+
+# convert to Factory Droid format
+bunx @every-env/compound-plugin install compound-engineering --to droid
+
+# convert to Cursor format
+bunx @every-env/compound-plugin install compound-engineering --to cursor
 ```
 
 Local dev:
@@ -31,8 +37,11 @@ bun run src/index.ts install ./plugins/compound-engineering --to opencode
 ```
 
 OpenCode output is written to `~/.config/opencode` by default, with `opencode.json` at the root and `agents/`, `skills/`, and `plugins/` alongside it.
-Both provider targets are experimental and may change as the formats evolve.
 Codex output is written to `~/.codex/prompts` and `~/.codex/skills`, with each Claude command converted into both a prompt and a skill (the prompt instructs Codex to load the corresponding skill). Generated Codex skill descriptions are truncated to 1024 characters (Codex limit).
+Droid output is written to `~/.factory/` with commands, droids (agents), and skills. Claude tool names are mapped to Factory equivalents (`Bash` → `Execute`, `Write` → `Create`, etc.) and namespace prefixes are stripped from commands.
+Cursor output is written to `.cursor/` with rules (`.mdc`), commands, skills, and `mcp.json`. Agents become "Agent Requested" rules (`alwaysApply: false`) so Cursor's AI activates them on demand. Works with both the Cursor IDE and Cursor CLI (`cursor-agent`) — they share the same `.cursor/` config directory.
+
+All provider targets are experimental and may change as the formats evolve.
 
 ## Sync Personal Config
 

package/docs/index.html

@@ -4,7 +4,7 @@
 <head>
   <meta charset="utf-8" />
   <title>Compounding Engineering - AI-Powered Development Tools for Claude Code</title>
-  <meta content="Your code reviews just got 12 expert opinions in 30 seconds. 28 specialized agents, 24 workflow commands, and 15 skills that make today's work easier than yesterday's." name="description" />
+  <meta content="Your code reviews just got 12 expert opinions in 30 seconds. 29 specialized agents, 23 workflow commands, and 18 skills that make today's work easier than yesterday's." name="description" />
   <meta content="width=device-width, initial-scale=1" name="viewport" />
 
   <!-- Open Graph -->
@@ -12,7 +12,7 @@
   <meta property="og:site_name" content="Compounding Engineering" />
   <meta property="og:locale" content="en_US" />
   <meta property="og:title" content="Compounding Engineering - AI Development Tools" />
-  <meta property="og:description" content="Get 12 expert code reviews in 30 seconds. 28 specialized agents that make today's work easier than yesterday's." />
+  <meta property="og:description" content="Get 12 expert code reviews in 30 seconds. 29 specialized agents that make today's work easier than yesterday's." />
   <meta name="twitter:card" content="summary_large_image" />
   <meta name="twitter:title" content="Compounding Engineering" />
   <meta name="twitter:description" content="12 expert code reviews in 30 seconds. Make today's work easier than yesterday's." />
@@ -155,13 +155,13 @@
         <div class="hero-decoration"></div>
         <div class="heading hero centered">
           <a href="https://github.com/EveryInc/compound-engineering-plugin/releases" class="eyebrow">
-            <i class="fa-solid fa-rocket"></i> Version 2.28.0 released!
+            <i class="fa-solid fa-rocket"></i> Version 2.32.2 released!
           </a>
           <h1 class="balanced" style="margin-bottom: 32px;">
             Your Code Reviews Just Got 12 Expert Opinions. In 30 Seconds.
           </h1>
           <p class="paragraph m secondary balanced" style="margin-bottom: 32px;">
-            Here's what happened when we shipped yesterday: security audit, performance analysis, architectural review, pattern detection, and eight more specialized checks—all running in parallel. No meetings. No waiting. Just answers. That's compounding engineering: 28 specialized agents, 24 workflow commands, and 15 skills that make today's work easier than yesterday's.
+            Here's what happened when we shipped yesterday: security audit, performance analysis, architectural review, pattern detection, and eight more specialized checks—all running in parallel. No meetings. No waiting. Just answers. That's compounding engineering: 29 specialized agents, 23 workflow commands, and 18 skills that make today's work easier than yesterday's.
           </p>
           <div class="button-group margin-paragraph centered">
             <a href="#install" class="button primary">
@@ -179,17 +179,17 @@
         <div class="stats-container">
           <div class="stat-card">
             <div class="stat-icon"><i class="fa-solid fa-users-gear"></i></div>
-            <div class="stat-number">28</div>
+            <div class="stat-number">29</div>
             <div class="stat-label">Specialized Agents</div>
           </div>
           <div class="stat-card">
             <div class="stat-icon"><i class="fa-solid fa-terminal"></i></div>
-            <div class="stat-number">24</div>
+            <div class="stat-number">23</div>
             <div class="stat-label">Slash Commands</div>
           </div>
           <div class="stat-card">
             <div class="stat-icon"><i class="fa-solid fa-wand-magic-sparkles"></i></div>
-            <div class="stat-number">15</div>
+            <div class="stat-number">18</div>
             <div class="stat-label">Intelligent Skills</div>
           </div>
           <div class="stat-card">
@@ -244,7 +244,7 @@
                 The <code>security-sentinel</code> has checked 10,000 PRs for SQL injection. The <code>kieran-rails-reviewer</code> never approves a controller with business logic. They don't get tired, don't skip Friday afternoon reviews, don't forget the conventions you agreed on in March. Run <code>/work</code> and watch your plan execute with quality gates that actually enforce your standards—every single time.
               </p>
               <div class="pillar-tools">
-                <span class="tool-tag">27 specialized agents</span>
+                <span class="tool-tag">29 specialized agents</span>
                 <span class="tool-tag">/work</span>
                 <span class="tool-tag">dhh-rails-style skill</span>
                 <span class="tool-tag">git-worktree skill</span>
@@ -292,7 +292,7 @@
       <section id="agents">
         <div class="heading">
           <h2 class="no-top-margin">
-            <i class="fa-solid fa-users-gear color-accent"></i> 27 Specialized Agents
+            <i class="fa-solid fa-users-gear color-accent"></i> 29 Specialized Agents
           </h2>
           <p class="paragraph m secondary">
             Think of them as coworkers who never quit. The security-sentinel has seen every SQL injection variant. The kieran-rails-reviewer enforces conventions with zero compromise. The performance-oracle spots N+1 queries while you're still reading the PR. Run them solo or launch twelve in parallel—your choice.
@@ -531,7 +531,7 @@
       <section id="commands">
         <div class="heading">
           <h2 class="no-top-margin">
-            <i class="fa-solid fa-terminal color-accent"></i> 19 Powerful Commands
+            <i class="fa-solid fa-terminal color-accent"></i> 23 Powerful Commands
           </h2>
           <p class="paragraph m secondary">
             Slash commands that replace entire workflows. <code>/review</code> is your code review committee. <code>/plan</code> is your research team. <code>/triage</code> sorts 50 todos in the time it takes you to read five. Each one automates hours of work into a single line.
@@ -683,7 +683,7 @@
       <section id="skills">
         <div class="heading">
           <h2 class="no-top-margin">
-            <i class="fa-solid fa-wand-magic-sparkles color-accent"></i> 12 Intelligent Skills
+            <i class="fa-solid fa-wand-magic-sparkles color-accent"></i> 18 Intelligent Skills
           </h2>
           <p class="paragraph m secondary">
             Domain expertise on tap. Need to write a Ruby gem? The andrew-kane-gem-writer knows the patterns Andrew uses in 50+ popular gems. Building a Rails app? The dhh-rails-style enforces 37signals conventions. Generating images? The gemini-imagegen has Google's AI on speed dial. Just invoke the skill and watch it work.
@@ -825,7 +825,7 @@
       <section id="mcp-servers">
         <div class="heading">
           <h2 class="no-top-margin">
-            <i class="fa-solid fa-server color-accent"></i> Two MCP Servers
+            <i class="fa-solid fa-server color-accent"></i> 1 MCP Server
           </h2>
           <p class="paragraph m secondary">
             Playwright gives Claude a browser—it can click buttons, take screenshots, fill forms, and validate what your users actually see. Context7 gives it instant access to docs for 100+ frameworks. Need to know how Next.js handles dynamic routes? Context7 fetches the answer in real-time instead of hallucinating from outdated training data.
@@ -989,7 +989,7 @@ skill: gemini-imagegen</code></pre>
           <span class="cta-badge"><i class="fa-solid fa-bolt"></i> Free & Open Source</span>
           <h2>Install Once. Compound Forever.</h2>
           <p class="paragraph m cta-subheading">
-            <strong>Your next code review takes 30 seconds.</strong> The one after that? Even faster. That's compounding. Get 27 expert agents, 19 workflow commands, and 12 specialized skills working for you right now.
+            <strong>Your next code review takes 30 seconds.</strong> The one after that? Even faster. That's compounding. Get 29 expert agents, 23 workflow commands, and 18 specialized skills working for you right now.
           </p>
           <div class="button-group margin-paragraph centered">
             <a href="#install" class="button primary cta-primary">

package/docs/pages/changelog.html

@@ -48,6 +48,8 @@
         <div class="nav-section">
           <h3>On This Page</h3>
           <ul>
+            <li><a href="#v2.32.2">v2.32.2</a></li>
+            <li><a href="#v2.32.1">v2.32.1</a></li>
             <li><a href="#v2.6.0">v2.6.0</a></li>
             <li><a href="#v2.5.0">v2.5.0</a></li>
             <li><a href="#v2.4.1">v2.4.1</a></li>
@@ -86,6 +88,43 @@
           <a href="https://keepachangelog.com/">Keep a Changelog</a> conventions.
         </p>
 
+        <!-- Version 2.32.2 -->
+        <section id="v2.32.2" class="version-section">
+          <div class="version-header">
+            <h2>v2.32.2</h2>
+            <span class="version-date">2026-02-12</span>
+          </div>
+
+          <div class="changelog-category changed">
+            <h3><i class="fa-solid fa-arrows-rotate"></i> Changed</h3>
+            <ul>
+              <li>
+                <strong><code>/release-docs</code> command moved from plugin to local <code>.claude/commands/</code></strong> -
+                This is a repository maintenance command and should not be distributed to users. Command count reduced from 24 to 23.
+              </li>
+            </ul>
+          </div>
+        </section>
+
+        <!-- Version 2.32.1 -->
+        <section id="v2.32.1" class="version-section">
+          <div class="version-header">
+            <h2>v2.32.1</h2>
+            <span class="version-date">2026-02-12</span>
+          </div>
+
+          <div class="changelog-category changed">
+            <h3><i class="fa-solid fa-arrows-rotate"></i> Changed</h3>
+            <ul>
+              <li>
+                <strong><code>/workflows:review</code> command</strong> - Added <code>learnings-researcher</code>
+                agent to the parallel review phase. The review now searches <code>docs/solutions/</code> for past
+                issues related to the PR's modules and patterns, surfacing "Known Pattern" findings during synthesis.
+              </li>
+            </ul>
+          </div>
+        </section>
+
         <!-- Version 2.6.0 -->
         <section id="v2.6.0" class="version-section">
           <div class="version-header">

package/docs/plans/2026-02-08-feat-convert-local-md-settings-for-opencode-codex-plan.md

@@ -0,0 +1,143 @@
+---
+title: Convert .local.md Settings for OpenCode and Codex
+type: feat
+date: 2026-02-08
+---
+
+# Convert .local.md Settings for OpenCode and Codex
+
+## Overview
+
+PR #124 introduces `.claude/compound-engineering.local.md` — a YAML frontmatter settings file that workflow commands (`review.md`, `work.md`) read at runtime to decide which agents to run. The conversion script already handles agents, commands, skills, hooks, and MCP servers. It does **not** handle `.local.md` settings files.
+
+The question: can OpenCode and Codex support this same pattern? And what does the converter need to do?
+
+## Analysis: What `.local.md` Actually Does
+
+The settings file does two things:
+
+1. **YAML frontmatter** with structured config: `review_agents: [list]`, `plan_review_agents: [list]`
+2. **Markdown body** with free-text instructions passed to review agents as context
+
+The commands (`review.md`, `work.md`) read this file at runtime using the Read tool and use the values to decide which Task agents to spawn. This is **prompt-level logic** — it's instructions in the command body telling the AI "read this file, parse it, act on it."
+
+## Key Insight: This Already Works
+
+The converter already converts `review.md` and `work.md` command bodies verbatim (for OpenCode) or as generated skills (for Codex). The instructions that say "Read `.claude/compound-engineering.local.md`" are just markdown text inside the command body. When the converter outputs them:
+
+- **OpenCode**: The command template includes the full body. The AI reads it, follows the instructions, reads the settings file.
+- **Codex**: The command becomes a prompt + generated skill. The skill body includes the instructions. The AI reads it, follows the instructions, reads the settings file.
+
+**The `.local.md` file itself is not a plugin component** — it's a runtime artifact created per-project by the user (via `/compound-engineering-setup`). The converter doesn't need to bundle it.
+
+## What Needs Attention
+
+### 1. Setup Command Has `disable-model-invocation: true`
+
+`setup.md` has `disable-model-invocation: true`. The converter already handles this correctly:
+
+- **OpenCode** (`claude-to-opencode.ts:117`): Skips commands with `disableModelInvocation`
+- **Codex** (`claude-to-codex.ts:22`): Filters them out of prompts and generated skills
+
+This means `/compound-engineering-setup` won't be auto-invocable in either target. That's correct — it's a deliberate user action. But it also means users of the converted plugin have **no way to run setup**. They'd need to manually create the `.local.md` file.
+
+### 2. The `.local.md` File Path Is Claude-Specific
+
+The commands reference `.claude/compound-engineering.local.md`. In OpenCode, the equivalent directory is `.opencode/`. In Codex, it's `.codex/`. The converter currently does **no text rewriting** of file paths inside command bodies.
+
+### 3. Slash Command References in Config-Aware Sections
+
+The commands say things like "Run `/compound-engineering-setup` to create a settings file." The Codex converter already transforms `/command-name` → `/prompts:command-name`, but since setup has `disable-model-invocation`, there's no matching prompt. This reference becomes a dead link.
+
+### 4. `Task {agent-name}(...)` Syntax in Review Commands
+
+`review.md` uses `Task {agent-name}(PR content)` — the Codex converter already transforms these to `$skill-name` references. OpenCode passes them through as template text.
+
+## Proposed Solution
+
+### Phase 1: Add Settings File Path Rewriting to Converters
+
+Both converters should rewrite `.claude/` paths inside command bodies to the target-appropriate directory.
+
+**File:** `src/converters/claude-to-opencode.ts`
+
+Add a `transformContentForOpenCode(body)` function that replaces:
+- `.claude/compound-engineering.local.md` → `.opencode/compound-engineering.local.md`
+- `~/.claude/compound-engineering.local.md` → `~/.config/opencode/compound-engineering.local.md`
+
+Apply it in `convertCommands()` to the command body before storing as template.
+
+**File:** `src/converters/claude-to-codex.ts`
+
+Extend `transformContentForCodex(body)` to also replace:
+- `.claude/compound-engineering.local.md` → `.codex/compound-engineering.local.md`
+- `~/.claude/compound-engineering.local.md` → `~/.codex/compound-engineering.local.md`
+
+### Phase 2: Generate Setup Equivalent for Each Target
+
+Since `setup.md` is excluded by `disable-model-invocation`, the converter should generate a **target-native setup instruction** that tells users how to create the settings file.
+
+**Option A: Include setup as a non-auto-invocable command anyway** (recommended)
+
+Change the converters to include `disable-model-invocation` commands but mark them appropriately:
+- **OpenCode**: Include in command map but add a `manual: true` flag or comment
+- **Codex**: Include as a prompt (user can still invoke it manually via `/prompts:compound-engineering-setup`)
+
+This is the simplest approach — the setup instructions are useful even if not auto-triggered.
+
+**Option B: Generate a README/instructions file**
+
+Create a `compound-engineering-settings.md` file in the output that documents how to create the settings file for the target platform. More complex, less useful.
+
+**Recommendation: Option A** — just stop filtering out `disable-model-invocation` commands entirely. Both OpenCode and Codex support user-invoked commands/prompts. The flag exists to prevent Claude from auto-invoking during conversation, not to hide the command entirely.
+
+### Phase 3: Update Tests
+
+**File:** `tests/converter.test.ts`
+
+- Add test that `.claude/` paths in command bodies are rewritten to `.opencode/` paths
+- Update existing `disable-model-invocation` test to verify the command IS included (if Option A)
+
+**File:** `tests/codex-converter.test.ts`
+
+- Add test that `.claude/` paths are rewritten to `.codex/` paths
+- Add test that setup command is included as a prompt (if Option A)
+- Add test that slash command references to setup are preserved correctly
+
+### Phase 4: Add Fixture for Settings-Aware Command
+
+**File:** `tests/fixtures/sample-plugin/commands/settings-aware-command.md`
+
+```markdown
+---
+name: workflows:review
+description: Run comprehensive code reviews
+---
+
+Read `.claude/compound-engineering.local.md` for agent config.
+If not found, use defaults.
+Run `/compound-engineering-setup` to create settings.
+```
+
+Test that the converter rewrites the paths and command references correctly.
+
+## Acceptance Criteria
+
+- [ ] OpenCode converter rewrites `.claude/` → `.opencode/` in command bodies
+- [ ] Codex converter rewrites `.claude/` → `.codex/` in command/skill bodies
+- [ ] Global path `~/.claude/` rewritten to target-appropriate global path
+- [ ] `disable-model-invocation` commands are included (not filtered) in both targets
+- [ ] Tests cover path rewriting for both targets
+- [ ] Tests cover setup command inclusion
+- [ ] Existing tests still pass
+
+## What We're NOT Doing
+
+- Not bundling the `.local.md` file itself (it's user-created per-project)
+- Not converting YAML frontmatter format (both targets can read `.md` files with YAML)
+- Not adding target-specific setup wizards (the instructions in the command body work across all targets)
+- Not rewriting `AskUserQuestion` tool references (all three platforms support equivalent interactive tools)
+
+## Complexity Assessment
+
+This is a **small change** — mostly string replacement in the converters plus updating the `disable-model-invocation` filter. The `.local.md` pattern is prompt-level instructions, not a proprietary API. It works anywhere an AI can read a file and follow instructions.

package/docs/plans/2026-02-08-feat-simplify-plugin-settings-plan.md

@@ -0,0 +1,195 @@
+---
+title: Simplify Plugin Settings with .local.md Pattern
+type: feat
+date: 2026-02-08
+---
+
+# Simplify Plugin Settings
+
+## Overview
+
+Replace the 486-line `/compound-engineering-setup` wizard and JSON config with the `.local.md` plugin-settings pattern. Make agent configuration dead simple: a YAML frontmatter file users edit directly, with a lightweight setup command that generates the template.
+
+## Problem Statement
+
+The current branch (`feat/compound-engineering-setup`) has:
+- A 486-line setup command with Quick/Advanced/Minimal modes, add/remove loops, custom agent discovery
+- JSON config file (`.claude/compound-engineering.json`) — not the plugin-settings convention
+- Config-loading boilerplate that would be duplicated across 4 workflow commands
+- Over-engineered for "which agents should review my code?"
+
+Meanwhile, the workflow commands on main have hardcoded agent lists that can't be customized per-project.
+
+## Proposed Solution
+
+Use `.claude/compound-engineering.local.md` with YAML frontmatter. Three simple changes:
+
+1. **Rewrite `setup.md`** (486 → ~60 lines) — detect project type, create template file
+2. **Add config reading to workflow commands** (~5 lines each) — read file, fall back to defaults
+3. **Config is optional** — everything works without it via auto-detection
+
+### Settings File Format
+
+```markdown
+---
+review_agents: [kieran-rails-reviewer, code-simplicity-reviewer, security-sentinel]
+plan_review_agents: [kieran-rails-reviewer, code-simplicity-reviewer]
+---
+
+# Review Context
+
+Any extra instructions for review agents go here.
+Focus on N+1 queries — we've had issues in the brief system.
+Skip agent-native checks for internal admin pages.
+```
+
+That's it. No `conditionalAgents`, no `options`, no `customAgents` mapping. Conditional agents (migration, frontend, architecture, data) stay hardcoded in the review command — they trigger based on file patterns, not config.
+
+## Implementation Plan
+
+### Phase 1: Rewrite setup.md
+
+**File:** `plugins/compound-engineering/commands/setup.md`
+**From:** 486 lines → **To:** ~60 lines
+
+The setup command should:
+
+- [x] Detect project type (Gemfile+Rails, tsconfig, pyproject.toml, etc.)
+- [x] Check if `.claude/compound-engineering.local.md` already exists
+- [x] If exists: show current config, ask if user wants to regenerate
+- [x] If not: create `.claude/compound-engineering.local.md` with smart defaults for detected type
+- [x] Display the file path and tell user they can edit it directly
+- [x] No wizard, no multi-step AskUserQuestion flows, no modify loops
+
+**Default agents by project type:**
+
+| Type | review_agents | plan_review_agents |
+|------|--------------|-------------------|
+| Rails | kieran-rails-reviewer, dhh-rails-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle | kieran-rails-reviewer, code-simplicity-reviewer |
+| Python | kieran-python-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle | kieran-python-reviewer, code-simplicity-reviewer |
+| TypeScript | kieran-typescript-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle | kieran-typescript-reviewer, code-simplicity-reviewer |
+| General | code-simplicity-reviewer, security-sentinel, performance-oracle | code-simplicity-reviewer, architecture-strategist |
+
+### Phase 2: Update review.md
+
+**File:** `plugins/compound-engineering/commands/workflows/review.md`
+**Change:** Replace hardcoded agent list (lines 64-81) with config-aware section
+
+Add before the parallel agents section (~5 lines):
+
+```markdown
+#### Load Review Agents
+
+Read `.claude/compound-engineering.local.md` (project) or `~/.claude/compound-engineering.local.md` (global).
+If found, use `review_agents` from YAML frontmatter. If not found, auto-detect project type and use defaults:
+- Rails: kieran-rails-reviewer, dhh-rails-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle
+- Python: kieran-python-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle
+- TypeScript: kieran-typescript-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle
+- General: code-simplicity-reviewer, security-sentinel, performance-oracle
+
+Run all review agents in parallel using Task tool.
+```
+
+**Keep conditional agents hardcoded** — they trigger on file patterns (db/migrate, *.ts, etc.), not user preference. This is correct behavior.
+
+**Add `schema-drift-detector` as a conditional agent** — currently exists as an agent but isn't wired into any command. Add it to the migrations conditional block:
+
+```markdown
+**MIGRATIONS: If PR contains database migrations or schema.rb changes:**
+
+- Task schema-drift-detector(PR content) - Detects unrelated schema.rb changes (run FIRST)
+- Task data-migration-expert(PR content) - Validates ID mappings, rollback safety
+- Task deployment-verification-agent(PR content) - Go/No-Go deployment checklist
+
+**When to run:** PR includes `db/migrate/*.rb` OR `db/schema.rb`
+```
+
+`schema-drift-detector` should run first per its own docs — catches drift before other DB reviewers waste time on unrelated changes.
+
+### Phase 3: Update work.md
+
+**File:** `plugins/compound-engineering/commands/workflows/work.md`
+**Change:** Replace hardcoded agent list in "Consider Reviewer Agents" section (lines 180-193)
+
+Replace with:
+
+```markdown
+If review agents are needed, read from `.claude/compound-engineering.local.md` frontmatter (`review_agents`).
+If no config, use project-appropriate defaults. Run in parallel with Task tool.
+```
+
+### Phase 4: Update compound.md
+
+**File:** `plugins/compound-engineering/commands/workflows/compound.md`
+**Change:** Update Phase 3 "Optional Enhancement" (lines 92-98) and "Applicable Specialized Agents" section (lines 214-234)
+
+The specialized agents in compound.md are problem-type-based (performance → performance-oracle, security → security-sentinel). These should stay hardcoded — they're not "review agents", they're domain experts triggered by problem category. No config needed.
+
+**Only change:** Add a note that users can customize review agents via `/compound-engineering-setup`, but don't add config-reading logic here.
+
+## Acceptance Criteria
+
+- [ ] `setup.md` is under 80 lines
+- [ ] Running `/compound-engineering-setup` creates `.claude/compound-engineering.local.md` with correct defaults
+- [ ] Running `/compound-engineering-setup` when config exists shows current config and asks before overwriting
+- [ ] `/workflows:review` reads agents from `.local.md` when present
+- [ ] `/workflows:review` falls back to auto-detected defaults when no config
+- [ ] `/workflows:work` reads agents from `.local.md` when present
+- [ ] `compound.md` unchanged except for a reference to the setup command
+- [ ] No JSON config files — only `.local.md`
+- [ ] Config file is optional — everything works without it
+- [ ] Conditional agents (migrations, frontend, architecture, data) remain hardcoded in review.md
+
+### Phase 5: Structural Cleanup
+
+**5a. Delete `technical_review.md`**
+
+`commands/technical_review.md` is a one-line command (`Have @agent-dhh-rails-reviewer @agent-kieran-rails-reviewer @agent-code-simplicity-reviewer review...`) with `disable-model-invocation: true`. It duplicates the `/plan_review` skill. Delete it.
+
+- [x] Delete `plugins/compound-engineering/commands/technical_review.md`
+
+**5b. Add `disable-model-invocation: true` to `setup.md`**
+
+The setup command is deliberate — users run it explicitly. It should not be auto-invoked.
+
+- [x] Add `disable-model-invocation: true` to `setup.md` frontmatter
+
+**5c. Update component counts**
+
+After changes: 29 agents, 24 commands (25 - 1 deleted technical_review), 18 skills, 1 MCP.
+
+Wait — with setup.md added and technical_review.md deleted: 25 - 1 = 24. Same as main. Verify actual count after changes.
+
+- [x] Update `plugin.json` description with correct counts
+- [x] Update `marketplace.json` description with correct counts
+- [x] Update `README.md` component counts table
+
+**5d. Update CHANGELOG.md**
+
+- [x] Add entry for v2.32.0 documenting: settings support, schema-drift-detector wired in, technical_review removed
+
+## Acceptance Criteria
+
+- [ ] `setup.md` is under 80 lines
+- [ ] `setup.md` has `disable-model-invocation: true`
+- [ ] Running `/compound-engineering-setup` creates `.claude/compound-engineering.local.md` with correct defaults
+- [ ] Running `/compound-engineering-setup` when config exists shows current config and asks before overwriting
+- [ ] `/workflows:review` reads agents from `.local.md` when present
+- [ ] `/workflows:review` falls back to auto-detected defaults when no config
+- [ ] `/workflows:review` runs `schema-drift-detector` for PRs with migrations or schema.rb
+- [ ] `/workflows:work` reads agents from `.local.md` when present
+- [ ] `compound.md` unchanged except for a reference to the setup command
+- [ ] `technical_review.md` deleted
+- [ ] No JSON config files — only `.local.md`
+- [ ] Config file is optional — everything works without it
+- [ ] Conditional agents (migrations, frontend, architecture, data) remain hardcoded in review.md
+- [ ] Component counts match across plugin.json, marketplace.json, and README.md
+
+## What We're NOT Doing
+
+- No multi-step wizard (users edit the file directly)
+- No custom agent discovery (users add agent names to the YAML list)
+- No `conditionalAgents` config (stays hardcoded by file pattern)
+- No `options` object (agentNative, parallelReviews — not needed)
+- No global vs project distinction in the command (just check both paths)
+- No config-loading boilerplate duplicated across commands