diff --git a/README.md b/README.md
index 5499cd5..220fed4 100644
--- a/README.md
+++ b/README.md
@@ -1,645 +1,81 @@
# ๐ผ Code Conductor
-> โ ๏ธ **Repository Renamed**
-> This project was previously named **Conductor's Score** (`Code-Conductor`).
-> It has been renamed to **Code Conductor** (`code-conductor`) as of July 23, 2025.
-> GitHub redirects all URLs, but please update any bookmarks or references.
-
-**Transform your development workflow in 60 seconds.** From tweet discovery to AI agents shipping codeโthe GitHub-native coordination system that changes how you build.
-
-> *"Stop juggling tasks. Start orchestrating agents."*
-
-## ๐ **Why Developers Are Switching to Agentic Development**
-
-- โก **Focus on architecture, let agents handle implementation** - Spend time on what matters most
-- ๐ฏ **Zero config for 90% of projects** - Auto-detects your stack and configures optimal roles
-- ๐ **Smart AI code reviews** - Opt-in reviews when you need them, not spam on every PR
-- ๐ค **Smart agent roles** - Generalist "dev" handles most tasks, specialists for complex work
-- ๐ **Native GitHub integration** - Issues become tasks, Actions monitor health
-- ๐ **Self-healing coordination** - Automatic cleanup, heartbeat monitoring, stale work recovery
-
-*"From weekend side project to shipping product in weeks, not months."*
-
-## ๐ **NEW: Let Claude Code Do Everything For You**
-
-**Skip the manual setup.** Paste this into Claude Code and watch the magic happen:
-
-```
-I need to move faster. Install Code Conductor into this project so we can run multiple Claude Code agents at once.
-
-Execute: bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
-```
-
-Claude Code will handle everythingโinstallation, configuration, even creating your first task roadmap. **No GitHub token setup required!** The system uses GitHub's built-in authentication automatically. **[See more power prompts โ](CLAUDE_CODE_PROMPT.md)**
-
-## ๐ฏ **90% Stack Coverage - Your Tech is Supported**
+**Orchestrate multiple AI coding agents. Ship 10x faster.**
-Code Conductor automatically detects and configures for the most popular technology stacks:
+## The Problem
-### **Frontend & Full-Stack** (40% of projects)
-- **React/Next.js** - Auto-configures frontend & UI roles
-- **Vue/Nuxt** - Component-based development ready
-- **Angular** - Enterprise app support
-- **Svelte/SvelteKit** - Modern reactive apps
+You're using Claude Code to ship features, but you're still working sequentially. One task at a time. One PR at a time. Meanwhile, your backlog keeps growing.
-### **Backend & APIs** (35% of projects)
-- **Node.js** (Express, NestJS) - Microservices ready
-- **Python** (Django, Flask, FastAPI) - Web & ML support
-- **Go** (Gin, Echo, Fiber) - High-performance services
-- **Java/Kotlin** (Spring) - Enterprise backends
-- **PHP** (Laravel, Symfony) - Rapid development
-- **.NET Core** (ASP.NET) - Microsoft stack
+## The Solution
-### **Mobile & Desktop** (15% of projects)
-- **React Native** - Cross-platform mobile
-- **Flutter** - Native performance
-- **Tauri** - Lightweight desktop apps
-- **Electron** - Web-powered desktop
+Code Conductor lets you run multiple AI agents in parallelโeach working on different features simultaneously. No conflicts. No coordination overhead. Just pure, parallelized productivity.
-### **Specialized Roles Auto-Configured**
-Based on your stack, we automatically add:
-- ๐ค **code-reviewer** - AI agent role for reviewing pull requests
-- ๐จ **frontend** - UI/UX implementation
-- ๐ฑ **mobile** - Platform-specific features
-- ๐ง **devops** - CI/CD & infrastructure
-- ๐ **security** - Vulnerability scanning
-- ๐งฎ **ml-engineer** - ML model deployment
-- ๐ **data** - ETL & analytics
+**Transform your workflow:**
+- ๐ **Hours, not weeks** - Multiple agents tackle your backlog in parallel
+- ๐ **Zero merge conflicts** - Each agent works in isolated git worktrees
+- ๐ค **Works with Claude Code** - Your favorite AI assistant, multiplied
+- ๐ฏ **Self-managing** - Agents claim tasks, implement, and ship autonomously
-## โก **60-Second Setup**
+## Quick Start
-**One command. Instant AI coordination.**
-
-**Prerequisites for all options:** Git, Python 3.9-3.12, curl (for one-liner), and tar. Run from the root of an existing Git repository. **If using pyenv, ensure your active Python version (e.g., via `pyenv shell 3.12.x`) has Poetry installed if you prefer it; otherwise, the script falls back to pip.**
-
-### **Option 1: Universal One-Liner (Recommended - No Cloning Required)**
-Run this in your existing project's root directory to download and install Code Conductor directly:
+One command. 60 seconds. Done.
```bash
bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
```
-- This method avoids cloning the full Code Conductor repo and is ideal for integrating into existing projects without repository pollution.
-- The script will prompt before overwriting any existing installation.
-- **Security best practice:** Review the script at the raw URL before running.
-- **Pyenv users:** If Poetry install fails, switch to the Python version that has Poetry installed (e.g., `pyenv shell 3.10.13`) and re-run.
-
-
-
-
-
-### Option 2: Poetry (For Cloned Repo)
-```bash
-# Clone the repository
-git clone https://github.com/ryanmac/code-conductor.git
-cd code-conductor
-
-# Install with Poetry (auto-creates virtual environment)
-poetry install
-poetry run python setup.py
-```
-
-### Option 3: Pip + Virtual Environment (For Cloned Repo)
-```bash
-# Clone the repository
-git clone https://github.com/ryanmac/code-conductor.git
-cd code-conductor
-
-# Create virtual environment
-python3 -m venv .venv
-source .venv/bin/activate # On Windows: .venv\Scripts\activate
-
-# Install dependencies
-pip install -r requirements.txt
-
-# Run setup
-python setup.py
-```
-
-### Option 4: One-Command Install Script (For Cloned Repo)
-```bash
-# From the repository directory:
-./install.sh
-
-# Or with custom setup options:
-./install.sh --auto
-```
-
-**That's it.** No GitHub token setup requiredโthe system uses GitHub Actions' built-in authentication. Now create a GitHub Issue with `conductor:task` label, launch an agent via [Conductor.build](https://conductor.build) (macOS only as of 2024-07-22) or terminal workflow (all platforms), and watch it work.
-
-## ๐ **Upgrading Code Conductor**
-
-**Keep your Code Conductor installation up-to-date with the latest features!**
-
-### **Automatic Upgrade Detection**
-
-Simply run the same installation command in your project:
-
-```bash
-bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
-```
-
-The installer will:
-- โ
Detect your existing installation and version
-- โ
Prompt to upgrade, reinstall, or cancel
-- โ
Preserve your configurations and customizations
-- โ
Update only core scripts and workflows
-- โ
Show what's new after upgrading
-
-### **What Gets Updated**
-- `.conductor/scripts/` - Core conductor commands
-- `.conductor/roles/` - Latest role definitions
-- `.github/workflows/` - Updated GitHub Actions
-- `setup.py`, `requirements.txt` - Dependency updates
-
-### **What Gets Preserved**
-- `.conductor/config.yaml` - Your project configuration
-- `CLAUDE.md` - Your custom AI instructions
-- All existing tasks and work in progress
-- Git worktrees and agent states
-
-### **Using Claude Code for Upgrades**
-
-Want to upgrade in seconds? Copy this power prompt into Claude Code:
+The installer auto-detects your stack (React, Python, Go, etc.) and configures everything. No GitHub tokens. No complex setup.
+**Or let Claude Code install it for you:**
```
-We need the latest Code Conductor features. Upgrade our installation to unlock enhanced task management and duplicate prevention.
-
-Run: bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
-Choose option 1 (Upgrade) and verify with ./conductor status
-```
-
-**๐ See [CLAUDE_CODE_PROMPT.md](CLAUDE_CODE_PROMPT.md) for game-changing automation prompts** that transform your project into an agentic development powerhouse.
-
-## ๐ค **AI Agent Quick Start**
-
-**NEW: AI-first experience with automatic onboarding!**
-
-After setup, Code Conductor creates a `CLAUDE.md` file with AI agent instructions. For Claude Code or other AI coding assistants:
-
-```bash
-# The ONLY command AI agents need to know:
-./conductor start [role]
-```
-
-This single command:
-- โ
Shows your role and capabilities
-- โ
Lists available tasks (creates demo tasks if needed)
-- โ
Claims the best matching task automatically
-- โ
Creates an isolated git worktree
-- โ
Provides all context needed to start
-
-### The Perfect Kickoff Prompt
-
-Start any Claude Code session with this value-focused prompt:
-
-```
-Ultrathink: What task will create the most value? Find it, claim it, complete it.
-```
-
-This prompt:
-- Triggers deep analysis with "ultrathink"
-- Focuses on value creation over busy work
-- Provides clear action steps: find โ claim โ complete
-- Works with any role or project type
-
-**Pro tip**: Add this to your text expander (e.g., `;ustart`) for instant agent activation.
-
-### Example AI Agent Session
-
-```
-> ./conductor start frontend
-
-๐ค Code Conductor Agent: frontend
-==================================
-๐ Role: frontend
-
-๐ Available Tasks:
- #42: Implement dark mode toggle
- #43: [INIT] Discover project documentation and create task map
- #44: Add responsive navigation menu
-
-๐ฏ Claiming task...
-โ
Claimed task #42
-๐ Workspace: worktrees/agent-frontend-42
-
-Next: cd worktrees/agent-frontend-42
-```
-
-### AI Agent Workflow
-
-1. **Start work**: `./conductor start dev`
-2. **Implement**: Work in the created worktree
-3. **Complete**: `./conductor complete`
-4. **Repeat**: Automatically moves to next task
-
-### Smart Task Discovery
-
-For existing projects, Code Conductor creates a special discovery task that AI agents can claim to:
-- Map all project documentation
-- Identify implemented vs missing features
-- Generate 10-20 specific development tasks
-- Create proper GitHub issues automatically
-
-## How It Works
-
-1. **Setup Phase**: Use the universal installer (Option 1) or other setup methods to configure your project. The setup script detects your project type and configures roles.
-2. **Task Creation**: Create tasks via GitHub Issues with the `conductor:task` label
-3. **Agent Initialization**: Agents use the universal bootstrap to claim work
-4. **Isolated Development**: Each agent works in a git worktree to prevent conflicts
-5. **Automated Coordination**: GitHub Actions manage health, cleanup, and task flow
-
-## Architecture
-
-### Hybrid Role Model
-
-The system uses a hybrid approach optimized for efficiency:
-
-- **Default Role**: `dev` - A generalist that can handle any task without specific requirements
-- **Specialized Roles**: Optional roles like `devops`, `security` for complex domains
-
-This reduces the complexity of managing many agent types while maintaining quality for specialized work.
-
-### File Structure
-
-```
-.conductor/
-โโโ config.yaml # Project configuration with auto-detected stack
-โโโ roles/ # Role definitions
-โ โโโ dev.md # Default generalist
-โ โโโ code-reviewer.md # AI-powered PR reviewer
-โ โโโ frontend.md # UI/UX specialist
-โ โโโ mobile.md # Mobile app developer
-โ โโโ devops.md # CI/CD specialist
-โ โโโ security.md # Security specialist
-โ โโโ ml-engineer.md # ML/AI specialist
-โ โโโ data.md # Data engineer
-โโโ scripts/ # Automation scripts
-โ โโโ conductor # Universal AI agent command
-โ โโโ task-claim.py # Atomic task assignment
-โ โโโ create-review-task.py # Creates review tasks from PRs
-โ โโโ health-check.py # System monitoring
-โโโ examples/ # Stack-specific task templates
- โโโ nextjs-webapp/
- โโโ python-webapp/
- โโโ mobile-app/
- โโโ ...
-```
-
-## Configuration
-
-### Project Setup
-
-Run `python setup.py` to configure:
-
-- Project name and documentation location
-- Technology stack detection
-- Role selection (hybrid model)
-- Task management approach
-- GitHub integration settings
-
-### Role Definitions
-
-Each role has a Markdown file in `.conductor/roles/` defining:
-
-- Responsibilities
-- Task selection criteria
-- Required skills
-- Success metrics
-
-### Task Format
-
-Tasks are created as GitHub Issues with complete specifications:
-
-**Issue Title**: Implement authentication
-
-**Issue Body**:
-```markdown
-## Description
-Implement user authentication system for the application.
-
-## Specifications
-See: docs/auth-spec.md
-
-## Best Practices
-- Use JWT tokens
-- Implement refresh tokens
+I need to move faster. Install Code Conductor into this project so we can run multiple Claude Code agents at once.
-## Success Criteria
-- Tests: 100% coverage
-- Security: Pass security scan
+Execute: bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
```
-**Labels**:
-- `conductor:task` (required)
-- `effort:medium`
-- `priority:medium`
-- `skill:backend` (optional, for specialized tasks)
-
-## ๐ค AI Code Review - Smart, Opt-In Quality Gates
-
-Request AI code reviews when you need them - no more review spam for trivial changes:
-
-- ๐ฏ **Opt-in reviews** - Add `needs-review` label or comment `/conductor review` to request
-- ๐ **Security scanning** - Agents check for hardcoded secrets, SQL injection risks, unsafe operations
-- ๐ **Bug detection** - Comprehensive analysis for null references, race conditions, logic errors
-- ๐ก **Smart filtering** - Automatically skips docs-only changes, tiny PRs, and bot updates
-- ๐งช **Test coverage** - Suggests missing tests and edge cases
+## See It In Action
-### How It Works
-
-1. **Request a review** - Add `needs-review` label or comment `/conductor review` on your PR
-2. **Smart filtering** - System checks if review is needed (skips trivial changes)
-3. **Task creation** - Review task appears as GitHub Issue (only if needed)
-4. **Agent review** - AI agents claim and complete thorough code review
-5. **PR feedback** - Detailed review posted as PR comment
-
-### Automatic Skip Conditions
-- PRs with less than 10 lines changed
-- Documentation-only changes
-- Dependabot and bot PRs
-- PRs labeled with `skip-review`
-- Draft PRs
-
-### Triggering Reviews
```bash
-# Option 1: Add label
-gh pr edit 123 --add-label needs-review
-
-# Option 2: Comment on PR
-@conductor review # or /conductor review
-
-# Option 3: Manual workflow
-gh workflow run pr-review-tasks.yml -f pr_number=123
-```
+# Create a task (GitHub Issue)
+gh issue create --label "conductor:task" --title "Add dark mode toggle"
-## Agent Workflow
+# Launch an agent
+./conductor start frontend
-### Launching an Agent
+# Watch it work
+# โ Claims task #42
+# โ Creates isolated worktree
+# โ Implements feature
+# โ Opens pull request
+# โ Moves to next task
-**Option A: Conductor Desktop App (macOS only)**
-```bash
-export AGENT_ROLE=dev # or devops, security, etc.
-./conductor start
-# Follow the printed instructions to open in Conductor app
-```
-
-**Option B: Multiple Terminals (All Platforms)**
-```bash
+# Launch more agents to parallelize
+./conductor start backend
./conductor start dev
-cd worktrees/agent-dev-[task_id]
-# Use tmux or screen for session management on Linux/Windows
-# Start your Claude Code session in the worktree
-```
-
-๐ **[See complete usage guide โ](docs/USAGE.md)**
-
-### Agent Lifecycle
-
-1. **Initialize**: Load role definition and check dependencies
-2. **Claim Task**: Atomically claim an available task
-3. **Create Worktree**: Isolated git workspace for conflict-free work
-4. **Execute Task**: Follow specifications and success criteria
-5. **Report Status**: Update heartbeat and progress
-6. **Complete/Idle**: Mark complete or report idle for cleanup
-
-### Universal Bootstrap Prompt
-
-The system provides a single prompt that works for any agent:
-
-```
-You are a Claude Code agent in a Code Conductor coordinated project.
-ROLE: {role}
-PROJECT: {project_name}
-
-1. Read your role definition: .conductor/roles/{role}.md
-2. Check available tasks: gh issue list -l 'conductor:task' --assignee '!*'
-3. Claim a task: python .conductor/scripts/task-claim.py --role {role}
-4. Work in your isolated worktree
-5. Commit and push changes when complete
-
-Note: Heartbeats are automatically managed by GitHub Actions.
-```
-
-## GitHub Integration
-
-### Issues as Tasks
-
-Create issues with the `conductor:task` label to automatically convert them to tasks.
-
-### Automated Workflows
-
-- **Health Monitoring**: Every 15 minutes
-- **Stale Cleanup**: Removes abandoned work
-- **Task Scheduling**: Processes dependencies
-- **Status Reports**: Updates dashboard issue
-
-## Monitoring
-
-### System Health
-
-```bash
-# Check local status
-python .conductor/scripts/health-check.py
-
-# View GitHub dashboard
-# Check issue with 'conductor:status' label
-```
-
-### Metrics Tracked
-
-- Active agents and their tasks
-- Available task queue depth
-- Completion rate and velocity
-- System health indicators
-
-## Examples
-
-### ๐ **Works with Your Stack**
-
-
-React Web App - Modern full-stack development
-
-```yaml
-project_name: harmony-webapp
-roles:
- default: dev
- specialized: [devops, ui-designer]
-build_validation:
- - npm test -- --coverage
- - npm run lint
- - npm run build
-```
-
-
-
-Chrome Extension + NextJS - Browser extension with web dashboard
-
-```yaml
-project_name: symphony-extension
-roles:
- default: dev
- specialized: [devops]
-protected_files:
- - packages/extension/manifest.json
-```
-
-
-
-Python Microservices - Scalable backend architecture
-
-```yaml
-project_name: api-platform
-roles:
- default: dev
- specialized: [devops, security]
-quality_checks:
- - pytest --cov=services
- - bandit -r services/
-```
-
-
-
-Tauri Desktop App - Cross-platform Rust + JS application
-
-```yaml
-project_name: desktop-app
-roles:
- default: dev
- specialized: [devops, security, rust-dev]
-matrix_builds: [ubuntu, macos, windows]
-```
-
-
-**Don't see your stack?** [Contribute an example](CONTRIBUTING.md) and help other developers!
-
-## Troubleshooting
-
-### Common Issues
-
-**No tasks available**
-- Check GitHub issues: gh issue list -l 'conductor:task'
-- Verify no file conflicts blocking tasks
-- Create new tasks: gh issue create --label 'conductor:task'
-
-**Agent can't claim tasks**
-- Run `python .conductor/scripts/dependency-check.py`
-- Ensure GitHub CLI is authenticated: `gh auth status`
-- Check git repository is clean: `git status`
-- Note: No GitHub token setup requiredโworkflows use built-in authentication
-
-**File conflicts**
-- System prevents these automatically
-- If occurs, check worktree isolation
-- Run cleanup: `python .conductor/scripts/cleanup-stale.py`
-
-### Debug Commands
-
-```bash
-# Check dependencies
-python .conductor/scripts/dependency-check.py
-
-# View system state
-gh issue list -l 'conductor:task' --json state,assignees,title
-
-# Force cleanup
-python .conductor/scripts/cleanup-stale.py --timeout 0
-
-# Validate configuration
-python .conductor/scripts/validate-config.py
```
-## Storage Footprint
-
-**Disk Usage**: Each agent creates a Git worktree (~50-200MB depending on project size)
-- **Cleanup**: Run `gtclean` weekly to remove abandoned worktrees
-- **Monitor**: Use `gtw` to list active worktrees
-- **Automatic**: Stale worktrees (>7 days inactive) are auto-archived via GitHub Actions
-
-**Pro tip**: Large projects should set `worktree_retention_days: 3` in config.yaml
-
-## Best Practices
-
-1. **Task Design**: Make tasks self-contained with clear specs
-2. **Duplicate Prevention**: Check existing issues before creating new ones - use `./conductor check-dup "title"`
-3. **Role Selection**: Start with dev-only, add specializations as needed
-4. **Regular Cleanup**: Let automation handle stale work
-5. **Monitor Health**: Check status issue regularly
-6. **Incremental Adoption**: Start small, expand as comfortable
-
-See also: [Duplicate Prevention Guide](docs/DUPLICATE_PREVENTION.md) for detailed strategies
-
-## Development Setup
-
-### Prerequisites
-- Python 3.9-3.12
-- Git
-- GitHub CLI (optional, for issue integration)
-
-### Local Development
-```bash
-# Clone and setup
-git clone https://github.com/ryanmac/code-conductor.git
-cd code-conductor
-
-# Install with Poetry (recommended)
-poetry install
-
-# Or with pip
-python3 -m venv .venv
-source .venv/bin/activate
-pip install -r requirements.txt
-
-# Run tests
-poetry run pytest tests/ -v
-# or
-python -m pytest tests/ -v
-
-# Run linting
-poetry run flake8 .conductor/scripts/ setup.py
-poetry run black --check .conductor/scripts/ setup.py
-```
-
-### CI/CD
-The project uses GitHub Actions for continuous integration:
-- **Linting**: flake8 and black formatting checks
-- **Testing**: pytest on multiple Python versions (3.9, 3.10, 3.11, 3.12)
-- **Security**: safety vulnerability scanning
-- **Platforms**: Ubuntu and macOS
-
-## Contributing
-
-This is a template repository. To contribute:
-
-1. Fork and improve
-2. Test with your project type
-3. Submit PRs with examples
-4. Share your adaptations
-
-### Development Guidelines
-- Follow PEP 8 style guidelines
-- Add tests for new functionality
-- Update documentation for changes
-- Ensure CI passes before submitting PRs
-
-## License
+**The secret:** Each agent works in its own git worktreeโlike having multiple copies of your repo. Agent A refactors authentication while Agent B adds dark mode. Zero conflicts.
-MIT - See LICENSE file
+## Learn More
-## Support
+๐ **[Full Documentation โ](docs/)**
+- [Installation Guide](docs/INSTALLATION.md) - All setup options
+- [Stack Support](docs/STACK_SUPPORT.md) - Works with React, Vue, Python, Go, and more
+- [Architecture](docs/ARCHITECTURE.md) - How it all works under the hood
+- [AI Code Review](docs/AI_CODE_REVIEW.md) - Smart, opt-in PR reviews
+- [Troubleshooting](docs/TROUBLESHOOTING.md) - Common issues and solutions
-- ๐ [Issue Tracker](https://github.com/ryanmac/code-conductor/issues)
-- ๐ฌ [Discussions](https://github.com/ryanmac/code-conductor/discussions)
+๐ **[Power User Prompts](CLAUDE_CODE_PROMPT.md)** - Game-changing automation with Claude Code
-## ๐ฌ **Join the Community**
+## Community
- ๐ **Found a bug?** [Report it](https://github.com/ryanmac/code-conductor/issues)
- ๐ก **Have an idea?** [Start a discussion](https://github.com/ryanmac/code-conductor/discussions)
-- ๐ ๏ธ **Want to contribute?** [See our guide](CONTRIBUTING.md)
+- ๐ ๏ธ **Want to contribute?** [See our guide](.github/CONTRIBUTING.md)
- ๐ **Share your success** Mention [@ryanmac](https://x.com/ryanmac) with #CodeConductor
-**Built for [Conductor.build](https://conductor.build) and [Warp](https://www.warp.dev/) users who refuse to juggle tasks manually.**
+---
-*Transform your development workflow. One command. Infinite possibilities.* ๐ผ
+**Stop juggling tasks. Start shipping features.** ๐ผ
diff --git a/docs/AGENT_WORKFLOW.md b/docs/AGENT_WORKFLOW.md
new file mode 100644
index 0000000..230db23
--- /dev/null
+++ b/docs/AGENT_WORKFLOW.md
@@ -0,0 +1,113 @@
+# Agent Workflow
+
+## AI Agent Quick Start
+
+After setup, Code Conductor creates a `CLAUDE.md` file with AI agent instructions. For Claude Code or other AI coding assistants:
+
+```bash
+# The ONLY command AI agents need to know:
+./conductor start [role]
+```
+
+This single command:
+- โ
Shows your role and capabilities
+- โ
Lists available tasks (creates demo tasks if needed)
+- โ
Claims the best matching task automatically
+- โ
Creates an isolated git worktree
+- โ
Provides all context needed to start
+
+## The Perfect Kickoff Prompt
+
+Start any Claude Code session with this value-focused prompt:
+
+```
+Ultrathink: What task will create the most value? Find it, claim it, complete it.
+```
+
+This prompt:
+- Triggers deep analysis with "ultrathink"
+- Focuses on value creation over busy work
+- Provides clear action steps: find โ claim โ complete
+- Works with any role or project type
+
+**Pro tip**: Add this to your text expander (e.g., `;ustart`) for instant agent activation.
+
+## Example AI Agent Session
+
+```
+> ./conductor start frontend
+
+๐ค Code Conductor Agent: frontend
+==================================
+๐ Role: frontend
+
+๐ Available Tasks:
+ #42: Implement dark mode toggle
+ #43: [INIT] Discover project documentation and create task map
+ #44: Add responsive navigation menu
+
+๐ฏ Claiming task...
+โ
Claimed task #42
+๐ Workspace: worktrees/agent-frontend-42
+
+Next: cd worktrees/agent-frontend-42
+```
+
+## AI Agent Workflow
+
+1. **Start work**: `./conductor start dev`
+2. **Implement**: Work in the created worktree
+3. **Complete**: `./conductor complete`
+4. **Repeat**: Automatically moves to next task
+
+## Smart Task Discovery
+
+For existing projects, Code Conductor creates a special discovery task that AI agents can claim to:
+- Map all project documentation
+- Identify implemented vs missing features
+- Generate 10-20 specific development tasks
+- Create proper GitHub issues automatically
+
+## Launching an Agent
+
+**Option A: Conductor Desktop App (macOS only)**
+```bash
+export AGENT_ROLE=dev # or devops, security, etc.
+./conductor start
+# Follow the printed instructions to open in Conductor app
+```
+
+**Option B: Multiple Terminals (All Platforms)**
+```bash
+./conductor start dev
+cd worktrees/agent-dev-[task_id]
+# Use tmux or screen for session management on Linux/Windows
+# Start your Claude Code session in the worktree
+```
+
+## Agent Lifecycle
+
+1. **Initialize**: Load role definition and check dependencies
+2. **Claim Task**: Atomically claim an available task
+3. **Create Worktree**: Isolated git workspace for conflict-free work
+4. **Execute Task**: Follow specifications and success criteria
+5. **Report Status**: Update heartbeat and progress
+6. **Complete/Idle**: Mark complete or report idle for cleanup
+
+## Universal Bootstrap Prompt
+
+The system provides a single prompt that works for any agent:
+
+```
+You are a Claude Code agent in a Code Conductor coordinated project.
+ROLE: {role}
+PROJECT: {project_name}
+
+1. Read your role definition: .conductor/roles/{role}.md
+2. Check available tasks: gh issue list -l 'conductor:task' --assignee '!*'
+3. Claim a task: python .conductor/scripts/task-claim.py --role {role}
+4. Work in your isolated worktree
+5. Commit and push changes when complete
+
+Note: Heartbeats are automatically managed by GitHub Actions.
+```
\ No newline at end of file
diff --git a/docs/AI_CODE_REVIEW.md b/docs/AI_CODE_REVIEW.md
new file mode 100644
index 0000000..15e361d
--- /dev/null
+++ b/docs/AI_CODE_REVIEW.md
@@ -0,0 +1,36 @@
+# AI Code Review - Smart, Opt-In Quality Gates
+
+Request AI code reviews when you need them - no more review spam for trivial changes:
+
+- ๐ฏ **Opt-in reviews** - Add `needs-review` label or comment `/conductor review` to request
+- ๐ **Security scanning** - Agents check for hardcoded secrets, SQL injection risks, unsafe operations
+- ๐ **Bug detection** - Comprehensive analysis for null references, race conditions, logic errors
+- ๐ก **Smart filtering** - Automatically skips docs-only changes, tiny PRs, and bot updates
+- ๐งช **Test coverage** - Suggests missing tests and edge cases
+
+## How It Works
+
+1. **Request a review** - Add `needs-review` label or comment `/conductor review` on your PR
+2. **Smart filtering** - System checks if review is needed (skips trivial changes)
+3. **Task creation** - Review task appears as GitHub Issue (only if needed)
+4. **Agent review** - AI agents claim and complete thorough code review
+5. **PR feedback** - Detailed review posted as PR comment
+
+## Automatic Skip Conditions
+- PRs with less than 10 lines changed
+- Documentation-only changes
+- Dependabot and bot PRs
+- PRs labeled with `skip-review`
+- Draft PRs
+
+## Triggering Reviews
+```bash
+# Option 1: Add label
+gh pr edit 123 --add-label needs-review
+
+# Option 2: Comment on PR
+@conductor review # or /conductor review
+
+# Option 3: Manual workflow
+gh workflow run pr-review-tasks.yml -f pr_number=123
+```
\ No newline at end of file
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
new file mode 100644
index 0000000..2f7bd15
--- /dev/null
+++ b/docs/ARCHITECTURE.md
@@ -0,0 +1,85 @@
+# Architecture
+
+## How It Works
+
+1. **Setup Phase**: Use the universal installer to configure your project. The setup script detects your project type and configures roles.
+2. **Task Creation**: Create tasks via GitHub Issues with the `conductor:task` label
+3. **Agent Initialization**: Agents use the universal bootstrap to claim work
+4. **Isolated Development**: Each agent works in a git worktree to prevent conflicts
+5. **Automated Coordination**: GitHub Actions manage health, cleanup, and task flow
+
+## Hybrid Role Model
+
+The system uses a hybrid approach optimized for efficiency:
+
+- **Default Role**: `dev` - A generalist that can handle any task without specific requirements
+- **Specialized Roles**: Optional roles like `devops`, `security` for complex domains
+
+This reduces the complexity of managing many agent types while maintaining quality for specialized work.
+
+## File Structure
+
+```
+.conductor/
+โโโ config.yaml # Project configuration with auto-detected stack
+โโโ roles/ # Role definitions
+โ โโโ dev.md # Default generalist
+โ โโโ code-reviewer.md # AI-powered PR reviewer
+โ โโโ frontend.md # UI/UX specialist
+โ โโโ mobile.md # Mobile app developer
+โ โโโ devops.md # CI/CD specialist
+โ โโโ security.md # Security specialist
+โ โโโ ml-engineer.md # ML/AI specialist
+โ โโโ data.md # Data engineer
+โโโ scripts/ # Automation scripts
+โ โโโ conductor # Universal AI agent command
+โ โโโ task-claim.py # Atomic task assignment
+โ โโโ create-review-task.py # Creates review tasks from PRs
+โ โโโ health-check.py # System monitoring
+โโโ examples/ # Stack-specific task templates
+ โโโ nextjs-webapp/
+ โโโ python-webapp/
+ โโโ mobile-app/
+ โโโ ...
+```
+
+## Core Components
+
+1. **Setup System** (`setup.py`)
+ - Interactive/auto configuration wizard
+ - Detects technology stack automatically
+ - Configures agent roles based on project type
+ - Creates GitHub workflows for automation
+
+2. **Task Management** (GitHub Issues)
+ - GitHub Issues with `conductor:task` label serve as tasks
+ - Issues have unique numbers, descriptions, success criteria
+ - GitHub's atomic operations prevent race conditions
+ - Native integration with GitHub Projects and Actions
+
+3. **Agent Roles** (`.conductor/roles/`)
+ - `dev.md` - Default generalist role for most tasks
+ - Specialized roles: `devops`, `security`, `frontend`, `mobile`, `ml-engineer`, `data`
+ - `code-reviewer` - AI-powered PR reviews (always included)
+ - Hybrid model: prefer `dev` role unless task requires specialization
+
+4. **Agent Coordination** (`.conductor/scripts/`)
+ - `conductor` - Universal agent command (primary interface)
+ - `task-claim.py` - Task assignment via GitHub Issue assignment
+ - `health-check.py` - Monitor agent heartbeats
+ - `cleanup-stale.py` - Remove abandoned work
+ - Git worktrees provide isolation between agents
+
+5. **GitHub Integration**
+ - Issues become tasks via `conductor:task` label
+ - Actions run health checks every 15 minutes
+ - AI code reviews on all PRs
+ - Status dashboard via `conductor:status` issue
+
+## Key Design Patterns
+
+1. **Atomic Operations**: GitHub's issue assignment API ensures atomic task claiming
+2. **Worktree Isolation**: Each agent works in separate git worktree (`worktrees/agent-{role}-{task_id}`)
+3. **Heartbeat System**: Agents update timestamps; stale work auto-cleaned after timeout
+4. **File Conflict Prevention**: Worktree isolation ensures agents work on separate branches
+5. **Self-Healing**: GitHub Actions monitor health, clean stale work, process issues
\ No newline at end of file
diff --git a/docs/BEST_PRACTICES.md b/docs/BEST_PRACTICES.md
new file mode 100644
index 0000000..51392ab
--- /dev/null
+++ b/docs/BEST_PRACTICES.md
@@ -0,0 +1,39 @@
+# Best Practices
+
+1. **Task Design**: Make tasks self-contained with clear specs
+2. **Duplicate Prevention**: Check existing issues before creating new ones - use `./conductor check-dup "title"`
+3. **Role Selection**: Start with dev-only, add specializations as needed
+4. **Regular Cleanup**: Let automation handle stale work
+5. **Monitor Health**: Check status issue regularly
+6. **Incremental Adoption**: Start small, expand as comfortable
+
+See also: [Duplicate Prevention Guide](DUPLICATE_PREVENTION.md) for detailed strategies
+
+## Task Format
+
+Tasks are created as GitHub Issues with complete specifications:
+
+**Issue Title**: Implement authentication
+
+**Issue Body**:
+```markdown
+## Description
+Implement user authentication system for the application.
+
+## Specifications
+See: docs/auth-spec.md
+
+## Best Practices
+- Use JWT tokens
+- Implement refresh tokens
+
+## Success Criteria
+- Tests: 100% coverage
+- Security: Pass security scan
+```
+
+**Labels**:
+- `conductor:task` (required)
+- `effort:medium`
+- `priority:medium`
+- `skill:backend` (optional, for specialized tasks)
\ No newline at end of file
diff --git a/docs/CONFIGURATION.md b/docs/CONFIGURATION.md
new file mode 100644
index 0000000..a72a972
--- /dev/null
+++ b/docs/CONFIGURATION.md
@@ -0,0 +1,52 @@
+# Configuration Guide
+
+## Project Configuration
+
+The main configuration file is `.conductor/config.yaml`, created during setup.
+
+### Configuration Structure
+
+```yaml
+# .conductor/config.yaml
+project_name: string
+documentation:
+ main: string (path to main docs)
+ additional: [array of paths]
+technology_stack:
+ languages: [detected languages]
+ frameworks: [detected frameworks]
+ tools: [detected build tools]
+roles:
+ default: "dev"
+ specialized: [list of specialized roles]
+github_integration:
+ enabled: boolean
+ issue_to_task: boolean
+ pr_reviews: boolean
+worktree_retention_days: number (default 7)
+```
+
+## Setup Options
+
+Run `python setup.py` to configure:
+
+- Project name and documentation location
+- Technology stack detection
+- Role selection (hybrid model)
+- Task management approach
+- GitHub integration settings
+
+## Role Definitions
+
+Each role has a Markdown file in `.conductor/roles/` defining:
+
+- Responsibilities
+- Task selection criteria
+- Required skills
+- Success metrics
+
+## Environment Variables
+
+- `AGENT_ROLE` - Set the default agent role
+- `CONDUCTOR_DEBUG` - Enable debug logging
+- `WORKTREE_BASE` - Override default worktree location
\ No newline at end of file
diff --git a/docs/DEVELOPMENT.md b/docs/DEVELOPMENT.md
new file mode 100644
index 0000000..b6910e8
--- /dev/null
+++ b/docs/DEVELOPMENT.md
@@ -0,0 +1,52 @@
+# Development Setup
+
+## Prerequisites
+- Python 3.9-3.12
+- Git
+- GitHub CLI (optional, for issue integration)
+
+## Local Development
+```bash
+# Clone and setup
+git clone https://github.com/ryanmac/code-conductor.git
+cd code-conductor
+
+# Install with Poetry (recommended)
+poetry install
+
+# Or with pip
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+
+# Run tests
+poetry run pytest tests/ -v
+# or
+python -m pytest tests/ -v
+
+# Run linting
+poetry run flake8 .conductor/scripts/ setup.py
+poetry run black --check .conductor/scripts/ setup.py
+```
+
+## CI/CD
+The project uses GitHub Actions for continuous integration:
+- **Linting**: flake8 and black formatting checks
+- **Testing**: pytest on multiple Python versions (3.9, 3.10, 3.11, 3.12)
+- **Security**: safety vulnerability scanning
+- **Platforms**: Ubuntu and macOS
+
+## Contributing
+
+This is a template repository. To contribute:
+
+1. Fork and improve
+2. Test with your project type
+3. Submit PRs with examples
+4. Share your adaptations
+
+### Development Guidelines
+- Follow PEP 8 style guidelines
+- Add tests for new functionality
+- Update documentation for changes
+- Ensure CI passes before submitting PRs
\ No newline at end of file
diff --git a/docs/EXAMPLES.md b/docs/EXAMPLES.md
new file mode 100644
index 0000000..56278b6
--- /dev/null
+++ b/docs/EXAMPLES.md
@@ -0,0 +1,49 @@
+# Examples - Works with Your Stack
+
+## React Web App - Modern full-stack development
+
+```yaml
+project_name: harmony-webapp
+roles:
+ default: dev
+ specialized: [devops, ui-designer]
+build_validation:
+ - npm test -- --coverage
+ - npm run lint
+ - npm run build
+```
+
+## Chrome Extension + NextJS - Browser extension with web dashboard
+
+```yaml
+project_name: symphony-extension
+roles:
+ default: dev
+ specialized: [devops]
+protected_files:
+ - packages/extension/manifest.json
+```
+
+## Python Microservices - Scalable backend architecture
+
+```yaml
+project_name: api-platform
+roles:
+ default: dev
+ specialized: [devops, security]
+quality_checks:
+ - pytest --cov=services
+ - bandit -r services/
+```
+
+## Tauri Desktop App - Cross-platform Rust + JS application
+
+```yaml
+project_name: desktop-app
+roles:
+ default: dev
+ specialized: [devops, security, rust-dev]
+matrix_builds: [ubuntu, macos, windows]
+```
+
+**Don't see your stack?** [Contribute an example](../CONTRIBUTING.md) and help other developers!
\ No newline at end of file
diff --git a/docs/GITHUB_INTEGRATION.md b/docs/GITHUB_INTEGRATION.md
new file mode 100644
index 0000000..8bb05bb
--- /dev/null
+++ b/docs/GITHUB_INTEGRATION.md
@@ -0,0 +1,59 @@
+# GitHub Integration
+
+## Issues as Tasks
+
+Create issues with the `conductor:task` label to automatically convert them to tasks.
+
+## Task Format
+
+Tasks are created as GitHub Issues with complete specifications:
+
+**Issue Title**: Implement authentication
+
+**Issue Body**:
+```markdown
+## Description
+Implement user authentication system for the application.
+
+## Specifications
+See: docs/auth-spec.md
+
+## Best Practices
+- Use JWT tokens
+- Implement refresh tokens
+
+## Success Criteria
+- Tests: 100% coverage
+- Security: Pass security scan
+```
+
+**Labels**:
+- `conductor:task` (required)
+- `effort:medium`
+- `priority:medium`
+- `skill:backend` (optional, for specialized tasks)
+
+## Automated Workflows
+
+- **Health Monitoring**: Every 15 minutes
+- **Stale Cleanup**: Removes abandoned work
+- **Task Scheduling**: Processes dependencies
+- **Status Reports**: Updates dashboard issue
+
+## GitHub Authentication
+
+Code Conductor uses GitHub's built-in authentication for all operations. No manual token setup is required for most users!
+
+### Default Setup (Recommended)
+The workflows generated by Code Conductor automatically use GitHub Actions' built-in `${{ github.token }}`, which provides:
+- โ
Read/write access to issues, pull requests, and code
+- โ
Ability to create and manage labels
+- โ
No setup required - works out of the box!
+
+### Advanced Setup (Optional)
+Only create a Personal Access Token if you need:
+- Higher API rate limits (5,000/hour instead of 1,000/hour)
+- Cross-repository access
+- Ability to trigger other workflows
+
+For detailed setup instructions and troubleshooting, see [.conductor/GITHUB_TOKEN_SETUP.md](../.conductor/GITHUB_TOKEN_SETUP.md).
\ No newline at end of file
diff --git a/docs/INSTALLATION.md b/docs/INSTALLATION.md
new file mode 100644
index 0000000..daa10bd
--- /dev/null
+++ b/docs/INSTALLATION.md
@@ -0,0 +1,66 @@
+# Installation Guide
+
+## Prerequisites
+All installation methods require:
+- Git
+- Python 3.9-3.12
+- curl (for one-liner)
+- tar
+
+Run from the root of an existing Git repository. **If using pyenv, ensure your active Python version (e.g., via `pyenv shell 3.12.x`) has Poetry installed if you prefer it; otherwise, the script falls back to pip.**
+
+## Option 1: Universal One-Liner (Recommended - No Cloning Required)
+Run this in your existing project's root directory to download and install Code Conductor directly:
+
+```bash
+bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
+```
+
+- This method avoids cloning the full Code Conductor repo and is ideal for integrating into existing projects without repository pollution.
+- The script will prompt before overwriting any existing installation.
+- **Security best practice:** Review the script at the raw URL before running.
+- **Pyenv users:** If Poetry install fails, switch to the Python version that has Poetry installed (e.g., `pyenv shell 3.10.13`) and re-run.
+
+
+
+
+## Option 2: Poetry (For Cloned Repo)
+```bash
+# Clone the repository
+git clone https://github.com/ryanmac/code-conductor.git
+cd code-conductor
+
+# Install with Poetry (auto-creates virtual environment)
+poetry install
+poetry run python setup.py
+```
+
+## Option 3: Pip + Virtual Environment (For Cloned Repo)
+```bash
+# Clone the repository
+git clone https://github.com/ryanmac/code-conductor.git
+cd code-conductor
+
+# Create virtual environment
+python3 -m venv .venv
+source .venv/bin/activate # On Windows: .venv\Scripts\activate
+
+# Install dependencies
+pip install -r requirements.txt
+
+# Run setup
+python setup.py
+```
+
+## Option 4: One-Command Install Script (For Cloned Repo)
+```bash
+# From the repository directory:
+./install.sh
+
+# Or with custom setup options:
+./install.sh --auto
+```
+
+## After Installation
+
+No GitHub token setup requiredโthe system uses GitHub Actions' built-in authentication. Now create a GitHub Issue with `conductor:task` label, launch an agent via [Conductor.build](https://conductor.build) (macOS only as of 2024-07-22) or terminal workflow (all platforms), and watch it work.
\ No newline at end of file
diff --git a/docs/MONITORING.md b/docs/MONITORING.md
new file mode 100644
index 0000000..13814cd
--- /dev/null
+++ b/docs/MONITORING.md
@@ -0,0 +1,49 @@
+# Monitoring
+
+## System Health
+
+```bash
+# Check local status
+python .conductor/scripts/health-check.py
+
+# View GitHub dashboard
+# Check issue with 'conductor:status' label
+```
+
+## Metrics Tracked
+
+- Active agents and their tasks
+- Available task queue depth
+- Completion rate and velocity
+- System health indicators
+
+## Health Monitoring
+
+GitHub Actions run health checks every 15 minutes to:
+- Monitor agent heartbeats
+- Clean up stale worktrees
+- Update status dashboard
+- Process new tasks
+
+## Status Dashboard
+
+The system automatically maintains a GitHub Issue with the `conductor:status` label that shows:
+- Currently active agents
+- Tasks in progress
+- Recent completions
+- System health status
+
+## Debugging
+
+Use these commands to diagnose issues:
+
+```bash
+# View all conductor tasks
+gh issue list -l 'conductor:task' --json state,assignees,title
+
+# Check agent worktrees
+ls -la worktrees/
+
+# View recent activity
+gh issue list -l 'conductor:task' --state all --limit 20
+```
\ No newline at end of file
diff --git a/docs/README.md b/docs/README.md
new file mode 100644
index 0000000..1bda549
--- /dev/null
+++ b/docs/README.md
@@ -0,0 +1,37 @@
+# Code Conductor Documentation
+
+Welcome to the comprehensive Code Conductor documentation. This directory contains detailed guides and references for all aspects of the system.
+
+## ๐ Documentation Index
+
+### Getting Started
+- [**Installation Guide**](INSTALLATION.md) - All installation methods and options
+- [**Usage Guide**](USAGE.md) - How to use Code Conductor effectively
+- [**Stack Support**](STACK_SUPPORT.md) - Supported technologies and frameworks
+
+### Core Concepts
+- [**Architecture**](ARCHITECTURE.md) - System design and components
+- [**Best Practices**](BEST_PRACTICES.md) - Recommended workflows and patterns
+- [**Duplicate Prevention**](DUPLICATE_PREVENTION.md) - Strategies to avoid duplicate work
+
+### Features
+- [**AI Code Review**](AI_CODE_REVIEW.md) - Smart pull request reviews
+- [**Examples**](EXAMPLES.md) - Configuration examples for different stacks
+
+### Operations
+- [**Upgrading**](UPGRADING.md) - How to update Code Conductor
+- [**Troubleshooting**](TROUBLESHOOTING.md) - Common issues and solutions
+- [**Development**](DEVELOPMENT.md) - Contributing to Code Conductor
+
+### Advanced Topics
+- [**GitHub Integration**](GITHUB_INTEGRATION.md) - Deep dive into GitHub features
+- [**Configuration**](CONFIGURATION.md) - Detailed configuration options
+- [**Agent Workflow**](AGENT_WORKFLOW.md) - How agents operate
+- [**Monitoring**](MONITORING.md) - System health and metrics
+- [**Storage**](STORAGE.md) - Managing disk usage
+
+## Quick Links
+
+- ๐ [Power User Prompts](../CLAUDE_CODE_PROMPT.md) - Advanced Claude Code automation
+- ๐ ๏ธ [Contributing Guide](../CONTRIBUTING.md) - Help improve Code Conductor
+- ๐ฌ [GitHub Discussions](https://github.com/ryanmac/code-conductor/discussions) - Community support
\ No newline at end of file
diff --git a/docs/STACK_SUPPORT.md b/docs/STACK_SUPPORT.md
new file mode 100644
index 0000000..e22704e
--- /dev/null
+++ b/docs/STACK_SUPPORT.md
@@ -0,0 +1,37 @@
+# ๐ฏ Stack Support & Coverage
+
+Code Conductor automatically detects and configures for the most popular technology stacks, covering 90% of modern projects.
+
+## Frontend & Full-Stack (40% of projects)
+- **React/Next.js** - Auto-configures frontend & UI roles
+- **Vue/Nuxt** - Component-based development ready
+- **Angular** - Enterprise app support
+- **Svelte/SvelteKit** - Modern reactive apps
+
+## Backend & APIs (35% of projects)
+- **Node.js** (Express, NestJS) - Microservices ready
+- **Python** (Django, Flask, FastAPI) - Web & ML support
+- **Go** (Gin, Echo, Fiber) - High-performance services
+- **Java/Kotlin** (Spring) - Enterprise backends
+- **PHP** (Laravel, Symfony) - Rapid development
+- **.NET Core** (ASP.NET) - Microsoft stack
+
+## Mobile & Desktop (15% of projects)
+- **React Native** - Cross-platform mobile
+- **Flutter** - Native performance
+- **Tauri** - Lightweight desktop apps
+- **Electron** - Web-powered desktop
+
+## Specialized Roles Auto-Configured
+Based on your stack, we automatically add:
+- ๐ค **code-reviewer** - AI agent role for reviewing pull requests
+- ๐จ **frontend** - UI/UX implementation
+- ๐ฑ **mobile** - Platform-specific features
+- ๐ง **devops** - CI/CD & infrastructure
+- ๐ **security** - Vulnerability scanning
+- ๐งฎ **ml-engineer** - ML model deployment
+- ๐ **data** - ETL & analytics
+
+## Don't See Your Stack?
+
+[Contribute an example](../CONTRIBUTING.md) and help other developers!
\ No newline at end of file
diff --git a/docs/STORAGE.md b/docs/STORAGE.md
new file mode 100644
index 0000000..c5abbe4
--- /dev/null
+++ b/docs/STORAGE.md
@@ -0,0 +1,50 @@
+# Storage Management
+
+## Disk Usage
+
+Each agent creates a Git worktree, which uses disk space:
+- Small projects: ~50MB per worktree
+- Medium projects: ~100-150MB per worktree
+- Large projects: ~200MB+ per worktree
+
+## Automatic Cleanup
+
+Stale worktrees are automatically cleaned up:
+- Default retention: 7 days
+- Configurable via `worktree_retention_days` in config.yaml
+- GitHub Actions run cleanup every 15 minutes
+
+## Manual Cleanup
+
+```bash
+# List all worktrees
+git worktree list
+
+# Remove specific worktree
+git worktree remove worktrees/agent-dev-42
+
+# Remove all stale worktrees
+python .conductor/scripts/cleanup-stale.py --timeout 0
+
+# Alias for quick cleanup (if configured)
+gtclean
+```
+
+## Best Practices
+
+1. **Large Projects**: Set `worktree_retention_days: 3` in config.yaml
+2. **Regular Cleanup**: Run `gtclean` weekly
+3. **Monitor Usage**: Use `du -sh worktrees/` to check disk usage
+4. **CI/CD Servers**: Set aggressive cleanup (1-2 days retention)
+
+## Storage Optimization
+
+For projects with limited disk space:
+
+```yaml
+# .conductor/config.yaml
+worktree_retention_days: 2
+max_concurrent_agents: 3
+```
+
+This limits the number of worktrees and reduces retention time.
\ No newline at end of file
diff --git a/docs/TROUBLESHOOTING.md b/docs/TROUBLESHOOTING.md
new file mode 100644
index 0000000..15f9019
--- /dev/null
+++ b/docs/TROUBLESHOOTING.md
@@ -0,0 +1,44 @@
+# Troubleshooting
+
+## Common Issues
+
+### No tasks available
+- Check GitHub issues: `gh issue list -l 'conductor:task'`
+- Verify no file conflicts blocking tasks
+- Create new tasks: `gh issue create --label 'conductor:task'`
+
+### Agent can't claim tasks
+- Run `python .conductor/scripts/dependency-check.py`
+- Ensure GitHub CLI is authenticated: `gh auth status`
+- Check git repository is clean: `git status`
+- Note: No GitHub token setup requiredโworkflows use built-in authentication
+
+### File conflicts
+- System prevents these automatically
+- If occurs, check worktree isolation
+- Run cleanup: `python .conductor/scripts/cleanup-stale.py`
+
+## Debug Commands
+
+```bash
+# Check dependencies
+python .conductor/scripts/dependency-check.py
+
+# View system state
+gh issue list -l 'conductor:task' --json state,assignees,title
+
+# Force cleanup
+python .conductor/scripts/cleanup-stale.py --timeout 0
+
+# Validate configuration
+python .conductor/scripts/validate-config.py
+```
+
+## Storage Footprint
+
+**Disk Usage**: Each agent creates a Git worktree (~50-200MB depending on project size)
+- **Cleanup**: Run `gtclean` weekly to remove abandoned worktrees
+- **Monitor**: Use `gtw` to list active worktrees
+- **Automatic**: Stale worktrees (>7 days inactive) are auto-archived via GitHub Actions
+
+**Pro tip**: Large projects should set `worktree_retention_days: 3` in config.yaml
\ No newline at end of file
diff --git a/docs/UPGRADING.md b/docs/UPGRADING.md
new file mode 100644
index 0000000..0671b8a
--- /dev/null
+++ b/docs/UPGRADING.md
@@ -0,0 +1,43 @@
+# Upgrading Code Conductor
+
+Keep your Code Conductor installation up-to-date with the latest features!
+
+## Automatic Upgrade Detection
+
+Simply run the same installation command in your project:
+
+```bash
+bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
+```
+
+The installer will:
+- โ
Detect your existing installation and version
+- โ
Prompt to upgrade, reinstall, or cancel
+- โ
Preserve your configurations and customizations
+- โ
Update only core scripts and workflows
+- โ
Show what's new after upgrading
+
+## What Gets Updated
+- `.conductor/scripts/` - Core conductor commands
+- `.conductor/roles/` - Latest role definitions
+- `.github/workflows/` - Updated GitHub Actions
+- `setup.py`, `requirements.txt` - Dependency updates
+
+## What Gets Preserved
+- `.conductor/config.yaml` - Your project configuration
+- `CLAUDE.md` - Your custom AI instructions
+- All existing tasks and work in progress
+- Git worktrees and agent states
+
+## Using Claude Code for Upgrades
+
+Want to upgrade in seconds? Copy this power prompt into Claude Code:
+
+```
+We need the latest Code Conductor features. Upgrade our installation to unlock enhanced task management and duplicate prevention.
+
+Run: bash <(curl -fsSL https://raw.githubusercontent.com/ryanmac/code-conductor/main/conductor-init.sh)
+Choose option 1 (Upgrade) and verify with ./conductor status
+```
+
+**๐ See [CLAUDE_CODE_PROMPT.md](../CLAUDE_CODE_PROMPT.md) for game-changing automation prompts** that transform your project into an agentic development powerhouse.
\ No newline at end of file