diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index bfb2b57..6c98eb6 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -11,8 +11,8 @@
"plugins": [
{
"name": "compounding-engineering",
- "description": "AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 17 specialized agents, 6 commands, and 1 skill.",
- "version": "1.1.0",
+ "description": "AI-powered development tools that get smarter with every use. Make each unit of engineering work easier than the last. Includes 23 specialized agents, 16 commands, and 11 skills.",
+ "version": "2.6.0",
"author": {
"name": "Kieran Klaassen",
"url": "https://github.com/kieranklaassen",
diff --git a/.github/workflows/deploy-docs.yml b/.github/workflows/deploy-docs.yml
new file mode 100644
index 0000000..4b7b090
--- /dev/null
+++ b/.github/workflows/deploy-docs.yml
@@ -0,0 +1,39 @@
+name: Deploy Documentation to GitHub Pages
+
+on:
+ push:
+ branches: [main]
+ paths:
+ - 'plugins/compounding-engineering/docs/**'
+ workflow_dispatch:
+
+permissions:
+ contents: read
+ pages: write
+ id-token: write
+
+concurrency:
+ group: "pages"
+ cancel-in-progress: false
+
+jobs:
+ deploy:
+ environment:
+ name: github-pages
+ url: ${{ steps.deployment.outputs.page_url }}
+ runs-on: ubuntu-latest
+ steps:
+ - name: Checkout
+ uses: actions/checkout@v4
+
+ - name: Setup Pages
+ uses: actions/configure-pages@v4
+
+ - name: Upload artifact
+ uses: actions/upload-pages-artifact@v3
+ with:
+ path: 'plugins/compounding-engineering/docs'
+
+ - name: Deploy to GitHub Pages
+ id: deployment
+ uses: actions/deploy-pages@v4
diff --git a/CLAUDE.md b/CLAUDE.md
index 6066b41..2eee544 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -12,9 +12,15 @@ every-marketplace/
└── compounding-engineering/ # The actual plugin
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
- ├── agents/ # 17 specialized AI agents
- ├── commands/ # 6 slash commands
- ├── skills/ # 1 skill (gemini-imagegen)
+ ├── agents/ # 24 specialized AI agents
+ ├── commands/ # 13 slash commands (including /release-docs)
+ ├── skills/ # 11 skills
+ ├── mcp-servers/ # 2 MCP servers (playwright, context7)
+ ├── docs/ # Documentation site (static HTML/CSS/JS)
+ │ ├── index.html # Landing page
+ │ ├── css/ # Stylesheets (style.css, docs.css)
+ │ ├── js/ # JavaScript (main.js)
+ │ └── pages/ # Reference pages (agents, commands, skills, mcp-servers)
├── README.md # Plugin documentation
└── CHANGELOG.md # Version history
```
@@ -86,7 +92,21 @@ When adding new functionality, bump the version in:
- [ ] `plugins/compounding-engineering/CHANGELOG.md` → document changes
- [ ] `CLAUDE.md` → update structure diagram if needed
-#### 5. Validate JSON files
+#### 5. Rebuild documentation site
+
+Run the release-docs command to update all documentation pages:
+
+```bash
+claude /release-docs
+```
+
+This will:
+- Update stats on the landing page
+- Regenerate reference pages (agents, commands, skills, MCP servers)
+- Update the changelog page
+- Validate all counts match actual files
+
+#### 6. Validate JSON files
```bash
cat .claude-plugin/marketplace.json | jq .
@@ -167,6 +187,73 @@ Each plugin has its own plugin.json with detailed metadata:
}
```
+## Documentation Site
+
+The plugin includes a static documentation site at `plugins/compounding-engineering/docs/`. This site is built with plain HTML/CSS/JS (based on Evil Martians' LaunchKit template) and requires no build step to view.
+
+### Documentation Structure
+
+```
+docs/
+├── index.html # Landing page with stats and philosophy
+├── css/
+│ ├── style.css # Main styles (LaunchKit-based)
+│ └── docs.css # Documentation-specific styles
+├── js/
+│ └── main.js # Interactivity (theme toggle, mobile nav)
+└── pages/
+ ├── getting-started.html # Installation and quick start
+ ├── agents.html # All 24 agents reference
+ ├── commands.html # All 13 commands reference
+ ├── skills.html # All 11 skills reference
+ ├── mcp-servers.html # MCP servers reference
+ └── changelog.html # Version history
+```
+
+### Keeping Docs Up-to-Date
+
+**IMPORTANT:** After ANY change to agents, commands, skills, or MCP servers, run:
+
+```bash
+claude /release-docs
+```
+
+This command:
+1. Counts all current components
+2. Reads all agent/command/skill/MCP files
+3. Regenerates all reference pages
+4. Updates stats on the landing page
+5. Updates the changelog from CHANGELOG.md
+6. Validates counts match across all files
+
+### Manual Updates
+
+If you need to update docs manually:
+
+1. **Landing page stats** - Update the numbers in `docs/index.html`:
+ ```html
+ 24
+ 13
+ ```
+
+2. **Reference pages** - Each page in `docs/pages/` documents all components in that category
+
+3. **Changelog** - `docs/pages/changelog.html` mirrors `CHANGELOG.md` in HTML format
+
+### Viewing Docs Locally
+
+Since the docs are static HTML, you can view them directly:
+
+```bash
+# Open in browser
+open plugins/compounding-engineering/docs/index.html
+
+# Or start a local server
+cd plugins/compounding-engineering/docs
+python -m http.server 8000
+# Then visit http://localhost:8000
+```
+
## Testing Changes
### Test Locally
diff --git a/plugins/compounding-engineering/.claude-plugin/plugin.json b/plugins/compounding-engineering/.claude-plugin/plugin.json
index 7b50cd0..ebcf315 100644
--- a/plugins/compounding-engineering/.claude-plugin/plugin.json
+++ b/plugins/compounding-engineering/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "compounding-engineering",
- "version": "2.5.0",
- "description": "AI-powered development tools. 24 agents, 16 commands, 11 skills, 2 MCP servers for code review, research, design, and workflow automation.",
+ "version": "2.6.0",
+ "description": "AI-powered development tools. 23 agents, 16 commands, 11 skills, 2 MCP servers for code review, research, design, and workflow automation.",
"author": {
"name": "Kieran Klaassen",
"email": "kieran@every.to",
diff --git a/plugins/compounding-engineering/CHANGELOG.md b/plugins/compounding-engineering/CHANGELOG.md
index d749760..b2f2885 100644
--- a/plugins/compounding-engineering/CHANGELOG.md
+++ b/plugins/compounding-engineering/CHANGELOG.md
@@ -5,6 +5,12 @@ All notable changes to the compounding-engineering plugin will be documented in
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+## [2.6.0] - 2024-11-26
+
+### Removed
+
+- **`feedback-codifier` agent** - Removed from workflow agents. Agent count reduced from 24 to 23.
+
## [2.5.0] - 2024-11-25
### Added
diff --git a/plugins/compounding-engineering/README.md b/plugins/compounding-engineering/README.md
index 9e7e323..d53b110 100644
--- a/plugins/compounding-engineering/README.md
+++ b/plugins/compounding-engineering/README.md
@@ -6,7 +6,7 @@ AI-powered development tools that get smarter with every use. Make each unit of
| Component | Count |
|-----------|-------|
-| Agents | 24 |
+| Agents | 23 |
| Commands | 16 |
| Skills | 11 |
| MCP Servers | 2 |
@@ -47,13 +47,12 @@ Agents are organized into categories for easier discovery.
| `design-iterator` | Iteratively refine UI through systematic design iterations |
| `figma-design-sync` | Synchronize web implementations with Figma designs |
-### Workflow (6)
+### Workflow (5)
| Agent | Description |
|-------|-------------|
| `bug-reproduction-validator` | Systematically reproduce and validate bug reports |
| `every-style-editor` | Edit content to conform to Every's style guide |
-| `feedback-codifier` | Codify feedback patterns into reviewer agents |
| `lint` | Run linting and code quality checks on Ruby and ERB files |
| `pr-comment-resolver` | Address PR comments and implement fixes |
| `spec-flow-analyzer` | Analyze user flows and identify gaps in specifications |
diff --git a/plugins/compounding-engineering/agents/workflow/feedback-codifier.md b/plugins/compounding-engineering/agents/workflow/feedback-codifier.md
deleted file mode 100644
index 74e1286..0000000
--- a/plugins/compounding-engineering/agents/workflow/feedback-codifier.md
+++ /dev/null
@@ -1,48 +0,0 @@
----
-name: feedback-codifier
-description: Use this agent when you need to analyze and codify feedback patterns from code reviews or technical discussions to improve existing reviewer agents. Examples: Context: User has provided detailed feedback on a Rails implementation and wants to capture those insights. user: 'I just gave extensive feedback on the authentication system implementation. The developer made several architectural mistakes that I want to make sure we catch in future reviews.' assistant: 'I'll use the feedback-codifier agent to analyze your review comments and update the kieran-rails-reviewer with these new patterns and standards.' Since the user wants to codify their feedback patterns, use the feedback-codifier agent to extract insights and update reviewer configurations.Context: After a thorough code review session with multiple improvement suggestions. user: 'That was a great review session. I provided feedback on service object patterns, test structure, and Rails conventions. Let's capture this knowledge.' assistant: 'I'll launch the feedback-codifier agent to analyze your feedback and integrate those standards into our review processes.' The user wants to preserve and systematize their review insights, so use the feedback-codifier agent.
-model: opus
-color: cyan
----
-
-You are an expert feedback analyst and knowledge codification specialist. Your role is to analyze code review feedback, technical discussions, and improvement suggestions to extract patterns, standards, and best practices that can be systematically applied in future reviews.
-
-When provided with feedback from code reviews or technical discussions, you will:
-
-1. **Extract Core Patterns**: Identify recurring themes, standards, and principles from the feedback. Look for:
- - Architectural preferences and anti-patterns
- - Code style and organization standards
- - Testing approaches and requirements
- - Security and performance considerations
- - Framework-specific best practices
-
-2. **Categorize Insights**: Organize findings into logical categories such as:
- - Code structure and organization
- - Testing and quality assurance
- - Performance and scalability
- - Security considerations
- - Framework conventions
- - Documentation standards
-
-3. **Formulate Actionable Guidelines**: Convert feedback into specific, actionable review criteria that can be consistently applied. Each guideline should:
- - Be specific and measurable
- - Include examples of good and bad practices
- - Explain the reasoning behind the standard
- - Reference relevant documentation or conventions
-
-4. **Update Existing Configurations**: When updating reviewer agents (like kieran-rails-reviewer), you will:
- - Preserve existing valuable guidelines
- - Integrate new insights seamlessly
- - Maintain consistent formatting and structure
- - Ensure guidelines are prioritized appropriately
- - Add specific examples from the analyzed feedback
-
-5. **Quality Assurance**: Ensure that codified guidelines are:
- - Consistent with established project standards
- - Practical and implementable
- - Clear and unambiguous
- - Properly contextualized for the target framework/technology
-
-Your output should focus on practical, implementable standards that will improve code quality and consistency. Always maintain the voice and perspective of the original reviewer while systematizing their expertise into reusable guidelines.
-
-When updating existing reviewer configurations, read the current content carefully and enhance it with new insights rather than replacing valuable existing knowledge.
diff --git a/plugins/compounding-engineering/commands/deploy-docs.md b/plugins/compounding-engineering/commands/deploy-docs.md
new file mode 100644
index 0000000..d527956
--- /dev/null
+++ b/plugins/compounding-engineering/commands/deploy-docs.md
@@ -0,0 +1,112 @@
+---
+name: deploy-docs
+description: Validate and prepare documentation for GitHub Pages deployment
+---
+
+# Deploy Documentation Command
+
+Validate the documentation site and prepare it for GitHub Pages deployment.
+
+## Step 1: Validate Documentation
+
+Run these checks:
+
+```bash
+# Count components
+echo "Agents: $(ls plugins/compounding-engineering/agents/*.md | wc -l)"
+echo "Commands: $(ls plugins/compounding-engineering/commands/*.md | wc -l)"
+echo "Skills: $(ls -d plugins/compounding-engineering/skills/*/ 2>/dev/null | wc -l)"
+
+# Validate JSON
+cat .claude-plugin/marketplace.json | jq . > /dev/null && echo "✓ marketplace.json valid"
+cat plugins/compounding-engineering/.claude-plugin/plugin.json | jq . > /dev/null && echo "✓ plugin.json valid"
+
+# Check all HTML files exist
+for page in index agents commands skills mcp-servers changelog getting-started; do
+ if [ -f "plugins/compounding-engineering/docs/pages/${page}.html" ] || [ -f "plugins/compounding-engineering/docs/${page}.html" ]; then
+ echo "✓ ${page}.html exists"
+ else
+ echo "✗ ${page}.html MISSING"
+ fi
+done
+```
+
+## Step 2: Check for Uncommitted Changes
+
+```bash
+git status --porcelain plugins/compounding-engineering/docs/
+```
+
+If there are uncommitted changes, warn the user to commit first.
+
+## Step 3: Deployment Instructions
+
+Since GitHub Pages deployment requires a workflow file with special permissions, provide these instructions:
+
+### First-time Setup
+
+1. Create `.github/workflows/deploy-docs.yml` with the GitHub Pages workflow
+2. Go to repository Settings > Pages
+3. Set Source to "GitHub Actions"
+
+### Deploying
+
+After merging to `main`, the docs will auto-deploy. Or:
+
+1. Go to Actions tab
+2. Select "Deploy Documentation to GitHub Pages"
+3. Click "Run workflow"
+
+### Workflow File Content
+
+```yaml
+name: Deploy Documentation to GitHub Pages
+
+on:
+ push:
+ branches: [main]
+ paths:
+ - 'plugins/compounding-engineering/docs/**'
+ workflow_dispatch:
+
+permissions:
+ contents: read
+ pages: write
+ id-token: write
+
+concurrency:
+ group: "pages"
+ cancel-in-progress: false
+
+jobs:
+ deploy:
+ environment:
+ name: github-pages
+ url: ${{ steps.deployment.outputs.page_url }}
+ runs-on: ubuntu-latest
+ steps:
+ - uses: actions/checkout@v4
+ - uses: actions/configure-pages@v4
+ - uses: actions/upload-pages-artifact@v3
+ with:
+ path: 'plugins/compounding-engineering/docs'
+ - uses: actions/deploy-pages@v4
+```
+
+## Step 4: Report Status
+
+Provide a summary:
+
+```
+## Deployment Readiness
+
+✓ All HTML pages present
+✓ JSON files valid
+✓ Component counts match
+
+### Next Steps
+- [ ] Commit any pending changes
+- [ ] Push to main branch
+- [ ] Verify GitHub Pages workflow exists
+- [ ] Check deployment at https://everyinc.github.io/every-marketplace/
+```
diff --git a/plugins/compounding-engineering/commands/release-docs.md b/plugins/compounding-engineering/commands/release-docs.md
new file mode 100644
index 0000000..38215c9
--- /dev/null
+++ b/plugins/compounding-engineering/commands/release-docs.md
@@ -0,0 +1,211 @@
+---
+name: release-docs
+description: Build and update the documentation site with current plugin components
+argument-hint: "[optional: --dry-run to preview changes without writing]"
+---
+
+# Release Documentation Command
+
+You are a documentation generator for the compounding-engineering plugin. Your job is to ensure the documentation site at `plugins/compounding-engineering/docs/` is always up-to-date with the actual plugin components.
+
+## Overview
+
+The documentation site is a static HTML/CSS/JS site based on the Evil Martians LaunchKit template. It needs to be regenerated whenever:
+
+- Agents are added, removed, or modified
+- Commands are added, removed, or modified
+- Skills are added, removed, or modified
+- MCP servers are added, removed, or modified
+
+## Step 1: Inventory Current Components
+
+First, count and list all current components:
+
+```bash
+# Count agents
+ls plugins/compounding-engineering/agents/*.md | wc -l
+
+# Count commands
+ls plugins/compounding-engineering/commands/*.md | wc -l
+
+# Count skills
+ls -d plugins/compounding-engineering/skills/*/ 2>/dev/null | wc -l
+
+# Count MCP servers
+ls -d plugins/compounding-engineering/mcp-servers/*/ 2>/dev/null | wc -l
+```
+
+Read all component files to get their metadata:
+
+### Agents
+For each agent file in `plugins/compounding-engineering/agents/*.md`:
+- Extract the frontmatter (name, description)
+- Note the category (Review, Research, Workflow, Design, Docs)
+- Get key responsibilities from the content
+
+### Commands
+For each command file in `plugins/compounding-engineering/commands/*.md`:
+- Extract the frontmatter (name, description, argument-hint)
+- Categorize as Workflow or Utility command
+
+### Skills
+For each skill directory in `plugins/compounding-engineering/skills/*/`:
+- Read the SKILL.md file for frontmatter (name, description)
+- Note any scripts or supporting files
+
+### MCP Servers
+For each MCP server in `plugins/compounding-engineering/mcp-servers/*/`:
+- Read the configuration and README
+- List the tools provided
+
+## Step 2: Update Documentation Pages
+
+### 2a. Update `docs/index.html`
+
+Update the stats section with accurate counts:
+```html
+
+ AI-Powered Development Tools That Get Smarter With Every Use
+
+
+ Make each unit of engineering work easier than the last. 23 specialized agents, 16 powerful commands,
+ 11 intelligent skills, and two MCP servers for code review, research, design, and workflow automation.
+
+ Every unit of engineering work should make subsequent units of work easier—not harder.
+
+
+
+
+
+
+ "Most engineering creates linear value: you build a feature, it works, done.
+ Compounding engineering creates exponential value: each solved problem teaches the system,
+ each pattern becomes reusable, each review strengthens future reviews."
+
+
+
+
+
+
+
+
+
Plan
+
Understand before you build
+
+ Before writing a single line of code, gather context. Research agents explore
+ documentation, analyze git history, and find best practices. The /workflows:plan
+ command orchestrates three research agents in parallel to create comprehensive implementation plans.
+
+ Each agent brings deep domain knowledge. The kieran-rails-reviewer knows Rails
+ conventions like an expert. The security-sentinel catches OWASP vulnerabilities.
+ The /workflows:work command executes plans while maintaining quality gates.
+
+ The /workflows:review command launches 12 or more review agents in parallel: security,
+ performance, architecture, data integrity, patterns, and more. Findings are categorized by
+ severity (P1/P2/P3) and stored as actionable todo files.
+
+ Every solved problem should teach the system. The /workflows:codify command
+ captures solutions as searchable documentation with YAML frontmatter for fast lookup.
+
+ Each agent brings deep expertise in a specific domain. Run them individually or orchestrate
+ multiple agents in parallel for comprehensive analysis.
+
+
+
+
+
+
Review Agents (10)
+
+
+
+ kieran-rails-reviewer
+ Rails
+
+
Super senior Rails developer with impeccable taste. Applies strict conventions for Turbo Streams, namespacing, and the "duplication over complexity" philosophy.
+ claude agent kieran-rails-reviewer
+
+
+
+ dhh-rails-reviewer
+ Rails
+
+
Reviews code from DHH's perspective. Focus on Rails conventions, simplicity, and avoiding over-engineering.
+ claude agent dhh-rails-reviewer
+
+
+
+ kieran-python-reviewer
+ Python
+
+
Python code review with strict conventions. PEP 8 compliance, type hints, and Pythonic patterns.
+ claude agent kieran-python-reviewer
+
+
+
+ kieran-typescript-reviewer
+ TypeScript
+
+
TypeScript review with focus on type safety, modern patterns, and clean architecture.
+ claude agent kieran-typescript-reviewer
+
+
+
+ security-sentinel
+ Security
+
+
Security audits and vulnerability assessments. OWASP top 10, injection attacks, authentication flaws.
Analyze architectural decisions, compliance, and system design patterns.
+ claude agent architecture-strategist
+
+
+
+ data-integrity-guardian
+ Data
+
+
Database migrations and data integrity review. Schema changes, foreign keys, data consistency.
+ claude agent data-integrity-guardian
+
+
+
+ pattern-recognition-specialist
+ Patterns
+
+
Analyze code for patterns and anti-patterns. Design patterns, code smells, refactoring opportunities.
+ claude agent pattern-recognition-specialist
+
+
+
+ code-simplicity-reviewer
+ Quality
+
+
Final pass for simplicity and minimalism. Remove unnecessary complexity, improve readability.
+ claude agent code-simplicity-reviewer
+
+
+
+
+
+
+
Research Agents (four)
+
+
+
+ framework-docs-researcher
+ Research
+
+
Research framework documentation and best practices. Find official guidance and community patterns.
+ claude agent framework-docs-researcher
+
+
+
+ best-practices-researcher
+ Research
+
+
Gather external best practices and examples from the community and industry standards.
+ claude agent best-practices-researcher
+
+
+
+ git-history-analyzer
+ Git
+
+
Analyze git history and code evolution. Understand how code has changed and why.
+ claude agent git-history-analyzer
+
+
+
+ repo-research-analyst
+ Research
+
+
Research repository structure and conventions. Understand project patterns and organization.
+ claude agent repo-research-analyst
+
+
+
+
+
+
+
Design Agents (three)
+
+
+
+ design-iterator
+ Design
+
+
Iteratively refine UI through systematic design iterations with screenshots and feedback loops.
+ claude agent design-iterator
+
+
+
+ figma-design-sync
+ Figma
+
+
Synchronize web implementations with Figma designs. Pixel-perfect matching.
+ claude agent figma-design-sync
+
+
+
+ design-implementation-reviewer
+ Review
+
+
Verify UI implementations match Figma designs. Catch visual regressions.
+ claude agent design-implementation-reviewer
+
+
+
+
+
+
+
Workflow Agents (five)
+
+
+
+ bug-reproduction-validator
+ Bugs
+
+
Systematically reproduce and validate bug reports. Create minimal reproduction cases.
+ claude agent bug-reproduction-validator
+
+
+
+ pr-comment-resolver
+ PR
+
+
Address PR comments and implement fixes. Batch process review feedback.
+ claude agent pr-comment-resolver
+
+
+
+ lint
+ Quality
+
+
Run linting and code quality checks on Ruby and ERB files.
+ claude agent lint
+
+
+
+ spec-flow-analyzer
+ Testing
+
+
Analyze user flows and identify gaps in specifications.
+ claude agent spec-flow-analyzer
+
+
+
+ every-style-editor
+ Content
+
+
Edit content to conform to Every's style guide.
+ claude agent every-style-editor
+
+
+
+
+
+
+
Documentation Agent (one)
+
+
+
+ ankane-readme-writer
+ Docs
+
+
Create READMEs following Ankane-style template for Ruby gems. Clean, concise, comprehensive documentation that gets straight to the point.
+ claude agent ankane-readme-writer
+
+
+
+
+
+
+
+
+
+ 16 Powerful Commands
+
+
+ Slash commands for common workflows. From code review to bug triage,
+ these commands automate complex multi-step processes.
+
+
+
+
+
+
Workflow Commands
+
+
+
+ /workflows:plan
+ core
+
+
Create comprehensive implementation plans with research agents and stakeholder analysis.
+
+
+
+ /workflows:review
+ core
+
+
Run exhaustive code reviews using 12 or more parallel agents, ultra-thinking, and worktrees.
+
+
+
+ /workflows:work
+ core
+
+
Execute work items systematically with progress tracking and validation.
+
+
+
+ /workflows:codify
+ core
+
+
Document solved problems for the knowledge base. Turn learnings into reusable patterns.
+
+
+
+
+
+
+
Utility Commands
+
+
+
+ /changelog
+ util
+
+
Create engaging changelogs for recent merges.
+
+
+
+ /create-agent-skill
+ util
+
+
Create or edit Claude Code skills with expert guidance.
+
+
+
+ /generate_command
+ util
+
+
Generate new slash commands from templates.
+
+
+
+ /heal-skill
+ util
+
+
Fix skill documentation issues automatically.
+
+
+
+ /plan_review
+ util
+
+
Multi-agent plan review in parallel.
+
+
+
+ /prime
+ util
+
+
Prime/setup command for project initialization.
+
+
+
+ /report-bug
+ util
+
+
Report bugs in the plugin with structured templates.
+
+
+
+ /reproduce-bug
+ util
+
+
Reproduce bugs using logs and console output.
+
+
+
+ /triage
+ util
+
+
Triage and prioritize issues interactively.
+
+
+
+ /resolve_parallel
+ util
+
+
Resolve TODO comments in parallel.
+
+
+
+ /resolve_pr_parallel
+ util
+
+
Resolve PR comments in parallel.
+
+
+
+ /resolve_todo_parallel
+ util
+
+
Resolve file-based todos in parallel.
+
+
+
+
+
+
+
+
+
+ 11 Intelligent Skills
+
+
+ Skills provide deep domain expertise that Claude Code can invoke on-demand.
+ From Ruby gem patterns to image generation.
+
+
+
+
+
+
Development Tools
+
+
+
+ andrew-kane-gem-writer
+ Ruby
+
+
Write Ruby gems following Andrew Kane's patterns. Clean APIs, smart defaults, comprehensive testing.
+ skill: andrew-kane-gem-writer
+
+
+
+ dhh-ruby-style
+ Rails
+
+
Write Ruby/Rails code in DHH's 37signals style. Convention over configuration, beautiful code.
+ skill: dhh-ruby-style
+
+
+
+ dspy-ruby
+ AI
+
+
Build type-safe LLM applications with DSPy.rb. Structured prompting, optimization, providers.
+ skill: dspy-ruby
+
+
+
+ frontend-design
+ Design
+
+
Create production-grade frontend interfaces with modern CSS, responsive design, accessibility.
+ skill: frontend-design
+
+
+
+ create-agent-skills
+ Meta
+
+
Expert guidance for creating Claude Code skills. Templates, best practices, validation.
+ skill: create-agent-skills
+
+
+
+ skill-creator
+ Meta
+
+
Guide for creating effective Claude Code skills with structured workflows.
+ skill: skill-creator
+
+
+
+ codify-docs
+ Docs
+
+
Capture solved problems as categorized documentation with YAML schema.
+ skill: codify-docs
+
+
+
+
+
+
+
Content & Workflow
+
+
+
+ every-style-editor
+ Content
+
+
Review copy for Every's style guide compliance.
+ skill: every-style-editor
+
+
+
+ file-todos
+ Workflow
+
+
File-based todo tracking system with priorities and status.
+ skill: file-todos
+
+
+
+ git-worktree
+ Git
+
+
Manage Git worktrees for parallel development on multiple branches.
+ skill: git-worktree
+
+
+
+
+
+
+
Image Generation
+
+
+
+ gemini-imagegen
+ AI Images
+
+
+ Generate and edit images using Google's Gemini API. Text-to-image, image editing,
+ multi-turn refinement, and composition from up to 14 reference images.
+
+
+
+ Text-to-image generation
+
+
+ Image editing & manipulation
+
+
+ Multi-turn refinement
+
+
+ Multiple reference images (up to 14)
+
+
+ Google Search grounding (Pro)
+
+
+ skill: gemini-imagegen
+
Requires: GEMINI_API_KEY environment variable
+
+
+
+
+
+
+
+
+
+ Two MCP Servers
+
+
+ Model Context Protocol servers extend Claude Code's capabilities with
+ browser automation and framework documentation lookup.
+
+
+
+
+
+
+
+ Playwright
+
+
Browser automation for testing, screenshots, and web interactions.
+
+
Tools Provided: 6 tools
+
+
browser_navigate - Navigate to URLs
+
browser_take_screenshot - Take screenshots
+
browser_click - Click elements
+
browser_fill_form - Fill form fields
+
browser_snapshot - Get accessibility snapshot
+
browser_evaluate - Execute JavaScript
+
+
+
+
+
+
+ Context7
+
+
Framework documentation lookup for more than 100 frameworks.
+
+
Tools Provided: 2 tools
+
+
resolve-library-id - Find library ID
+
get-library-docs - Get documentation
+
+
Supports: Rails, React, Next.js, Vue, Django, Laravel, and more than 100 others
+
+
+
+
+
+
+
+
+
Get Started in Seconds
+
+ Install the plugin and start using AI-powered development tools immediately.
+
+
+
+
+
+
1
+
+
Add the Marketplace
+
+
claude /plugin marketplace add https://github.com/EveryInc/every-marketplace
+
+
+
+
+
2
+
+
Install the Plugin
+
+
claude /plugin install compounding-engineering
+
+
+
+
+
3
+
+
Start Using
+
+
# Run a code review
+/workflows:review PR#123
+
+# Use an agent
+claude agent kieran-rails-reviewer
+
+# Invoke a skill
+skill: gemini-imagegen
+
+
+
+
+
+
+
+
+
+
Frequently Asked Questions
+
+
+
+
+
What is Compounding Engineering?
+
+
+
+
+ Compounding Engineering is a philosophy that every unit of engineering work should make subsequent
+ units easier—not harder. This plugin embodies that philosophy with tools that learn from patterns,
+ automate repetitive tasks, and build institutional knowledge.
+
+
+
+
+
+
How do agents differ from skills?
+
+
+
+
+ Agents are specialized personas that can be invoked to perform specific tasks
+ (e.g., code review, research). They're called with claude agent [name].
+
+
+ Skills provide domain expertise that Claude Code can use on-demand. They include
+ reference materials, templates, and workflows. They're invoked with skill: [name].
+
+
+
+
+
+
Why aren't MCP servers loading automatically?
+
+
+
+
+ This is a known issue. As a workaround, manually add the MCP servers to your
+ .claude/settings.json file. See the README for the exact configuration.
+
+
+
+
+
+
Can I use this with languages other than Ruby/Rails?
+
+
+
+
+ Yes! While many agents are specialized for Rails, we also have Python and TypeScript reviewers.
+ The workflow commands, research agents, and skills like gemini-imagegen work with any language.
+
+
+
+
+
+
How do I create my own agents or skills?
+
+
+
+
+ Use the /create-agent-skill command or the create-agent-skills skill
+ for expert guidance. The skill includes templates, best practices, and validation workflows.
+
+
+
+
+
+
+
+
+
+ Free & Open Source
+
Transform Your Development Workflow in Minutes
+
+ Install once. Compound forever. Get 23 expert agents, 16 workflow commands, and 11 specialized skills working for you—starting now.
+
+ Complete documentation for all 23 specialized AI agents. Each agent brings deep expertise
+ in a specific domain and can be invoked individually or orchestrated together.
+
+
+
+
How to Use Agents
+
+
# Basic invocation
+claude agent [agent-name]
+
+# With a specific message
+claude agent [agent-name] "Your message here"
+
+# Examples
+claude agent kieran-rails-reviewer
+claude agent security-sentinel "Audit the payment flow"
+
+
+
+
+
+
Review Agents (10)
+
Code review agents that examine changes from multiple perspectives: conventions, security, performance, architecture, and quality.
+
+
+
+
kieran-rails-reviewer
+ Rails
+
+
+ Super senior Rails developer with impeccable taste and an exceptionally high bar for Rails code quality.
+ Reviews with strict conventions while being pragmatic on new isolated code.
+
+ Reviews and edits text content to conform to Every's specific style guide.
+
+
Style Checks
+
+
Title case in headlines, sentence case elsewhere
+
Company singular/plural usage
+
Remove overused words (actually, very, just)
+
Enforce active voice
+
Apply formatting rules (Oxford commas, em dashes)
+
+
+
claude agent every-style-editor
+
+
+
+
+
+
+
Design Agents (3)
+
Design agents that help with UI implementation, Figma synchronization, and iterative design refinement.
+
+
+
+
design-iterator
+ Design
+
+
+ Systematic UI/UX design refinement through iterative improvements.
+ Takes screenshots, analyzes, implements changes, and repeats.
+
+
Process
+
+
Take focused screenshots of target elements
+
Analyze current state and identify 3-5 improvements
+
Implement targeted CSS/design changes
+
Document changes made
+
Repeat for specified iterations (default 10)
+
+
+
claude agent design-iterator
+
+
+
+
+
+
figma-design-sync
+ Figma
+
+
+ Automatically detects and fixes visual differences between Figma designs and web implementations.
+ Uses Sonnet model.
+
+
Workflow
+
+
Extract design specifications from Figma
+
Capture implementation screenshots
+
Conduct systematic visual comparison
+
Make precise code changes to fix discrepancies
+
Verify implementation matches design
+
+
+
claude agent figma-design-sync
+
+
+
+
+
+
design-implementation-reviewer
+ Review
+
+
+ Verifies UI implementations match Figma design specifications.
+ Uses Opus model for detailed analysis.
+
+
Comparison Areas
+
+
Layouts and structure
+
Typography (fonts, sizes, weights)
+
Colors and themes
+
Spacing and alignment
+
Different viewport sizes
+
+
+
claude agent design-implementation-reviewer
+
+
+
+
+
+
+
Documentation Agent (1)
+
+
+
+
ankane-readme-writer
+ Docs
+
+
+ Creates/updates README files following Ankane-style template for Ruby gems.
+ Optimized for conciseness with every sentence kept to 15 words or less.
+
+ All notable changes to the compounding-engineering plugin. This project follows
+ Semantic Versioning and
+ Keep a Changelog conventions.
+
+
+
+
+
+
v2.6.0
+ 2024-11-26
+
+
+
+
Removed
+
+
+ feedback-codifier agent - Removed from workflow agents.
+ Agent count reduced from 24 to 23.
+
+
+
+
+
+
+
+
+
v2.5.0
+ 2024-11-25
+
+
+
+
Added
+
+
+ /report-bug command - New slash command for reporting bugs in the
+ compounding-engineering plugin. Provides a structured workflow that gathers bug information
+ through guided questions, collects environment details automatically, and creates a GitHub
+ issue in the EveryInc/every-marketplace repository.
+
+
+
+
+
+
+
+
+
v2.4.1
+ 2024-11-24
+
+
+
+
Improved
+
+
+ design-iterator agent - Added focused screenshot guidance: always capture
+ only the target element/area instead of full page screenshots. Includes browser_resize
+ recommendations, element-targeted screenshot workflow using browser_snapshot refs, and
+ explicit instruction to never use fullPage mode.
+
+
+
+
+
+
+
+
+
v2.4.0
+ 2024-11-24
+
+
+
+
Fixed
+
+
+ MCP Configuration - Moved MCP servers back to plugin.json
+ following working examples from anthropics/life-sciences plugins.
+
+
+ Context7 URL - Updated to use HTTP type with correct endpoint URL.
+
+
+
+
+
+
+
+
+
v2.3.0
+ 2024-11-24
+
+
+
+
Changed
+
+
+ MCP Configuration - Moved MCP servers from inline plugin.json
+ to separate .mcp.json file per Claude Code best practices.
+
+
+
+
+
+
+
+
+
v2.2.1
+ 2024-11-24
+
+
+
+
Fixed
+
+
+ Playwright MCP Server - Added missing "type": "stdio" field
+ required for MCP server configuration to load properly.
+
+
+
+
+
+
+
+
+
v2.2.0
+ 2024-11-24
+
+
+
+
Added
+
+
+ Context7 MCP Server - Bundled Context7 for instant framework documentation
+ lookup. Provides up-to-date docs for Rails, React, Next.js, and more than 100 other frameworks.
+
+
+
+
+
+
+
+
+
v2.1.0
+ 2024-11-24
+
+
+
+
Added
+
+
+ Playwright MCP Server - Bundled @playwright/mcp for browser
+ automation across all projects. Provides screenshot, navigation, click, fill, and evaluate tools.
+
+
+
+
+
+
Changed
+
+
Replaced all Puppeteer references with Playwright across agents and commands:
+
+
bug-reproduction-validator agent
+
design-iterator agent
+
design-implementation-reviewer agent
+
figma-design-sync agent
+
generate_command command
+
+
+
+
+
+
+
+
+
+
v2.0.2
+ 2024-11-24
+
+
+
+
Changed
+
+
+ design-iterator agent - Updated description to emphasize proactive usage
+ when design work isn't coming together on first attempt.
+
+
+
+
+
+
+
+
+
v2.0.1
+ 2024-11-24
+
+
+
+
Added
+
+
CLAUDE.md - Project instructions with versioning requirements
+ This guide will help you install, configure, and start using the Compounding Engineering plugin
+ for Claude Code. In about five minutes, you'll have access to 23 specialized agents, 16 commands,
+ 11 skills, and two MCP servers.
+
First, add the Every Marketplace to your Claude Code installation:
+
+
claude /plugin marketplace add https://github.com/EveryInc/every-marketplace
+
+
+
Step 2: Install the Plugin
+
Install the compounding-engineering plugin from the marketplace:
+
+
claude /plugin install compounding-engineering
+
+
+
Step 3: Verify Installation
+
Verify the plugin is installed correctly:
+
+
claude /plugin list
+
+
You should see compounding-engineering in the list of installed plugins.
+
+
+
+
+
Known Issue: MCP Servers
+
+ The bundled MCP servers (Playwright and Context7) may not load automatically.
+ See the MCP Configuration section for the workaround.
+
+
+
+
+
+
+
+
Quick Start
+
+
Here are the most common ways to use the plugin:
+
+
Run a Code Review
+
The /workflows:review command runs a comprehensive code review using multiple agents in parallel:
+
+
# Review a PR by number
+/workflows:review 123
+
+# Review the current branch
+/workflows:review
+
+# Review a specific branch
+/workflows:review feature/my-feature
+
+
+
Use a Specialized Agent
+
Invoke agents directly for specific tasks:
+
+
# Rails code review with Kieran's conventions
+claude agent kieran-rails-reviewer "Review the UserController"
+
+# Security audit
+claude agent security-sentinel "Audit authentication flow"
+
+# Research best practices
+claude agent best-practices-researcher "Find pagination patterns for Rails"
+
+
+
Invoke a Skill
+
Skills provide domain expertise on demand:
+
+
# Generate images with Gemini
+skill: gemini-imagegen
+
+# Write Ruby in DHH's style
+skill: dhh-ruby-style
+
+# Create a new Claude Code skill
+skill: create-agent-skills
+
+
+
+
+
+
Configuration
+
+
MCP Server Configuration
+
+ If MCP servers don't auto-load, add them manually to your .claude/settings.json:
+
+ Skills provide domain expertise that Claude Code can invoke on-demand.
+ Unlike agents (which are personas), skills are bodies of knowledge with
+ templates, references, and workflows.
+
+
+
Invoking Skills
+
+
# In your prompt, reference the skill
+skill: gemini-imagegen
+
+# Or ask Claude to use it
+"Use the dhh-ruby-style skill to refactor this code"
P2 Important - Should fix. Performance issues, architectural concerns, reliability problems.
+
P3 Nice-to-Have - Enhancements. Minor improvements, cleanup, documentation.
+
+
+
Working with Todo Files
+
Review findings are stored as todo files in the todos/ directory:
+
+
# List all pending todos
+ls todos/*-pending-*.md
+
+# Triage findings
+/triage
+
+# Resolve todos in parallel
+/resolve_todo_parallel
+
+
+
+
+
+
Creating Custom Agents
+
+
+ You can create custom agents tailored to your team's needs.
+ Agents are defined as markdown files with YAML frontmatter.
+
+
+
Agent File Structure
+
+
---
+name: my-custom-agent
+description: Brief description of what this agent does
+---
+
+# Agent Instructions
+
+You are [role description].
+
+## Your Responsibilities
+1. First responsibility
+2. Second responsibility
+
+## Guidelines
+- Guideline one
+- Guideline two
+
+
+
Agent Location
+
Place custom agents in:
+
+
.claude/agents/ - Project-specific agents
+
~/.claude/agents/ - User-wide agents
+
+
+
+
+
+
Use the Command
+
+ The easiest way to create agents is with the /create-agent-skill command
+ or the create-agent-skills skill.
+
+
+
+
+
+
+
+
Creating Custom Skills
+
+
+ Skills are more complex than agents. They can include references,
+ templates, workflows, and scripts.
+
---
+name: my-skill
+description: Brief description shown when skill is invoked
+---
+
+# Skill Title
+
+Detailed instructions for using this skill.
+
+## Quick Start
+...
+
+## Reference Materials
+The skill includes references in the `references/` directory.
+
+## Templates
+Use templates from the `templates/` directory.
+
+
+
+
+
+
Expert Guidance
+
+ Use skill: create-agent-skills for comprehensive guidance
+ on creating effective skills, including best practices and validation.
+
+ Model Context Protocol (MCP) servers extend Claude Code's capabilities with
+ browser automation and framework documentation lookup. The plugin bundles
+ two MCP servers that start automatically when enabled.
+
+
+
+
+
+
Known Issue: Auto-Loading
+
+ MCP servers may not load automatically when the plugin is installed.
+ See Manual Configuration for the workaround.
+
+
+
+
+
+
+
Playwright
+
+ Browser automation via @playwright/mcp. Enables taking screenshots,
+ clicking elements, filling forms, and executing JavaScript in a real browser.
+
+
+
Tools Provided
+
+
+
+
Tool
+
Description
+
+
+
+
+
browser_navigate
+
Navigate to a URL in the browser
+
+
+
browser_take_screenshot
+
Capture a screenshot of the current page or element
+
+
+
browser_click
+
Click on an element using CSS selector or text
+
+
+
browser_fill_form
+
Fill form fields with values
+
+
+
browser_snapshot
+
Get an accessibility tree snapshot of the page
+
+
+
browser_evaluate
+
Execute JavaScript code in the browser context
+
+
+
+
+
Use Cases
+
+
Design Iteration - Take screenshots for UI comparison
+
Testing - Automate browser interactions
+
Debugging - Inspect page state and DOM
+
Data Extraction - Scrape content from web pages
+
+
+
Example Usage
+
+
# The tools are available when the MCP server is running
+# Claude Code will use them automatically when appropriate
+
+# Example: Taking a screenshot for design review
+"Take a screenshot of the login page"
+
+# Example: Testing a form
+"Navigate to /signup and fill in the email field with test@example.com"
+ Framework documentation lookup via Context7 MCP. Provides access to
+ documentation for more than 100 frameworks and libraries.
+
+
+
Tools Provided
+
+
+
+
Tool
+
Description
+
+
+
+
+
resolve-library-id
+
Find the library ID for a framework or package
+
+
+
get-library-docs
+
Get documentation for a specific library
+
+
+
+
+
Supported Frameworks
+
Context7 supports more than 100 frameworks including:
+
+
+
Backend
+
+
Ruby on Rails
+
Django
+
Laravel
+
Express
+
FastAPI
+
Spring Boot
+
+
+
+
Frontend
+
+
React
+
Vue.js
+
Angular
+
Svelte
+
Next.js
+
Nuxt
+
+
+
+
Mobile
+
+
React Native
+
Flutter
+
SwiftUI
+
Kotlin
+
+
+
+
Tools & Libraries
+
+
Tailwind CSS
+
PostgreSQL
+
Redis
+
GraphQL
+
Prisma
+
And many more...
+
+
+
+
+
Example Usage
+
+
# Claude Code will use Context7 automatically for documentation lookups
+"Look up the Rails ActionCable documentation"
+
+"How does the useEffect hook work in React?"
+
+"What are the best practices for PostgreSQL indexes?"
After configuration, restart Claude Code and verify the servers are loaded:
+
+
# Check if MCP tools are available
+"What MCP tools do you have access to?"
+
+# Test Playwright
+"Take a screenshot of the current directory listing"
+
+# Test Context7
+"Look up Rails Active Record documentation"
+ Complete documentation for all 11 intelligent skills. Skills provide deep domain expertise
+ that Claude Code can invoke on-demand, including references, templates, and workflows.
+
+
+
+
How to Use Skills
+
+
# In your prompt, reference the skill
+skill: [skill-name]
+
+# Examples
+skill: gemini-imagegen
+skill: dhh-ruby-style
+skill: create-agent-skills
+
+
+
+
+
+
+
Skills vs Agents
+
+ Agents are specialized personas invoked with claude agent [name].
+ Skills are bodies of knowledge (references, templates, workflows) invoked with skill: [name].
+
+
+
+
+
+
+
Development Tools (7)
+
Skills for code generation, gem writing, and development patterns.
+
+
+
+
create-agent-skills
+ Meta
+
+
+ Expert guidance for creating, writing, building, and refining Claude Code Skills.
+ Use when working with SKILL.md files or authoring new skills.
+
+ Guide for creating effective skills with a 6-step process.
+
+
6-Step Process
+
+
Understand skill usage patterns with examples
+
Plan reusable skill contents
+
Initialize skill using template
+
Edit skill with clear instructions
+
Package skill into distributable zip
+
Iterate based on testing feedback
+
+
+
skill: skill-creator
+
+
+
+
+
+
dhh-ruby-style
+ Rails
+
+
+ Write Ruby and Rails code in DHH's distinctive 37signals style.
+ Triggers on Ruby/Rails code generation or when mentioning DHH, 37signals, Basecamp, HEY.
+
+
Key Patterns
+
+
REST Purity - 7 REST actions only
+
Fat Models - Business logic, authorization, broadcasting in models
+
Thin Controllers - 1-5 line actions
+
Current Attributes - Request context
+
Hotwire/Turbo - Model-level broadcasting
+
+
Ruby Syntax Preferences
+
+
Symbol arrays %i[...]
+
Modern hash syntax
+
Ternaries for simple conditionals
+
Bang methods for mutations
+
+
+
skill: dhh-ruby-style
+
+
+
+
+
+
andrew-kane-gem-writer
+ Ruby
+
+
+ Write Ruby gems following Andrew Kane's proven patterns and philosophy.
+ Based on 100+ gems with 374M+ downloads.
+
+
Philosophy
+
+
Simplicity over cleverness
+
Zero or minimal dependencies
+
Explicit code over metaprogramming
+
Rails integration without Rails coupling
+
+
Key Patterns
+
+
Class macro DSL for configuration
+
ActiveSupport.on_load for Rails integration
+
class << self with attr_accessor
+
Railtie pattern for hooks
+
Minitest (no RSpec)
+
+
Reference Files
+
+
references/module-organization.md
+
references/rails-integration.md
+
references/database-adapters.md
+
references/testing-patterns.md
+
+
+
skill: andrew-kane-gem-writer
+
+
+
+
+
+
dspy-ruby
+ AI
+
+
+ Build type-safe, composable LLM applications with DSPy.rb.
+ Use when implementing predictable AI features in Ruby.
+
+
Predictor Types
+
+
Predict - Basic inference
+
ChainOfThought - Reasoning with explanations
+
ReAct - Tool-using agents with iteration
+
CodeAct - Dynamic code generation
+
+
Supported Providers
+
+
OpenAI (GPT-4, GPT-4o-mini)
+
Anthropic Claude
+
Google Gemini
+
Ollama (free, local)
+
OpenRouter
+
+
Requirements
+
+
+
OPENAI_API_KEY
+
For OpenAI provider
+
+
+
ANTHROPIC_API_KEY
+
For Anthropic provider
+
+
+
GOOGLE_API_KEY
+
For Gemini provider
+
+
+
+
skill: dspy-ruby
+
+
+
+
+
+
frontend-design
+ Design
+
+
+ Create distinctive, production-grade frontend interfaces.
+ Generates creative, polished code that avoids generic AI aesthetics.
+
+
Design Thinking
+
+
Purpose - What is the interface for?
+
Tone - What feeling should it evoke?
+
Constraints - Technical and brand limitations
+
Differentiation - How to stand out
+
+
Focus Areas
+
+
Typography with distinctive font choices
+
Color & theme coherence with CSS variables
+
Motion and animation patterns
+
Spatial composition with asymmetry
+
Backgrounds (gradients, textures, patterns)
+
+
+
+
+
Avoids generic AI aesthetics like Inter fonts, purple gradients, and rounded corners everywhere.
+
+
+
+
skill: frontend-design
+
+
+
+
+
+
codify-docs
+ Docs
+
+
+ Capture solved problems as categorized documentation with YAML frontmatter for fast lookup.
+