Transform PRDs into shipped features using GitHub Issues and parallel AI agents.

Stop losing context. Eliminate task blocking. Reduce shipped bugs. This battle-tested system turns product requirements into production code with full traceability at every step.

# Install from GitHub
pip install git+https://github.com/automazeio/ccpm.git

The installer automatically:

• ✅ Installs GitHub CLI if needed
• ✅ Sets up GitHub authentication
• ✅ Installs required extensions
• ✅ Configures your environment

# Navigate to your project
cd /path/to/your/project

# Set up CCPM
ccpm setup .

# Initialize the PM system
ccpm init

# In Claude Code, create a comprehensive PRD
/pm:prd-new user-authentication

# Transform PRD into technical implementation plan
/pm:prd-parse user-authentication

# Break down and sync to GitHub in one command
/pm:epic-oneshot user-authentication

# Start implementing with parallel agents
/pm:issue-start 1234

🎉 That's it! You're now using spec-driven development with full GitHub integration.

graph LR
    A[PRD Creation] --> B[Epic Planning]
    B --> C[Task Decomposition]
    C --> D[GitHub Sync]
    D --> E[Parallel Execution]

1. 🧠 Brainstorm - Think deeper than comfortable
2. 📝 Document - Write specs that leave nothing to interpretation
3. 📐 Plan - Architect with explicit technical decisions
4. ⚡ Execute - Build exactly what was specified
5. 📊 Track - Maintain transparent progress at every step

• 🤝 True Team Collaboration - Multiple Claude instances work simultaneously
• 🔄 Seamless Human-AI Handoffs - Progress visible to everyone
• 📈 Scalable Beyond Solo Work - Add team members without friction
• 🎯 Single Source of Truth - Issues are the project state

Tip: Type /pm:help in Claude Code for a quick reference.

Traditional approach: One issue = One developer = Sequential work

Example: "Implement user authentication" becomes:

• Agent 1: Database schema and migrations
• Agent 2: Service layer and business logic
• Agent 3: API endpoints and middleware
• Agent 4: UI components and forms
• Agent 5: Tests and documentation

All running simultaneously in the same worktree.

• Main conversation stays strategic
• Each agent handles its own context in isolation
• Implementation details never pollute main thread
• Use specialized agents:
  • file-analyzer - Summarize logs and verbose outputs
  • code-analyzer - Search code and trace logic
  • test-runner - Execute tests with full analysis
  • parallel-worker - Coordinate parallel work streams

GitHub Issues enable:

• Multiple Claude instances working simultaneously
• Real-time progress visibility for all team members
• Seamless handoffs between AI and human developers
• Integration with existing GitHub workflows

.claude/
├── prds/              # Product Requirements Documents
├── epics/             # Implementation plans
│   └── [epic-name]/
│       ├── epic.md    # Technical plan
│       ├── [#].md     # Task files (synced with GitHub)
│       └── updates/   # Work-in-progress
├── agents/            # Specialized task agents
├── commands/pm/       # PM command definitions
└── context/           # Project-wide context

Ship faster with multiple agents working simultaneously. Tasks marked parallel: true enable conflict-free concurrent development.

Works with tools your team already uses. Issues are the source of truth, comments provide history, and there is no dependency on the Projects API.

Right tool for every job. Different agents for UI, API, and database work. Each reads requirements and posts updates automatically.

Every decision is documented. PRD → Epic → Task → Issue → Code → Commit. Complete audit trail from idea to production.

Focus on building, not managing. Intelligent prioritization, automatic context loading, and incremental sync when ready.

Teams using this system report:

• 89% less time lost to context switching – you'll use /compact and /clear a LOT less
• 5-8 parallel tasks vs 1 previously – editing/testing multiple files at the same time
• 75% reduction in bug rates – due to the breaking down features into detailed tasks
• Up to 3x faster feature delivery – based on feature size and complexity

# macOS
brew install gh

# Ubuntu/Debian
sudo apt install gh

# Windows
winget install --id GitHub.cli

python --version

# Install for current user only
pip install --user git+https://github.com/automazeio/ccpm.git

# Re-authenticate
gh auth login

# Check status
gh auth status

# Verify extensions
gh extension list

• 🐧 Linux - Ubuntu, Debian, Fedora, RHEL, etc.
• 🍎 macOS - Intel and Apple Silicon
• 🪟 Windows - 10, 11, Server 2019+

Claude Code PM was developed at Automaze for developers who ship, by developers who ship.

If Claude Code PM helps your team ship better software:

• ⭐ Star this repository to show your support
• 🐦 Follow @aroussi on X for updates and tips