claude-task-master 0.1.2

Autonomous task orchestration system that keeps Claude working until a goal is achieved

Claude Task Master

Autonomous task orchestration system that keeps Claude working until a goal is achieved.

Quick Start

# Install from PyPI
pip install claude-task-master

# Or with uv (recommended)
uv tool install claude-task-master

# Verify setup
claudetm doctor

# Run a task
cd your-project
claudetm start "Add user authentication with tests"

Overview

Claude Task Master uses the Claude Agent SDK to autonomously work on complex tasks. Give it a goal, and it will:

1. Plan - Analyze codebase and create a task list organized by PRs
2. Execute - Work through each task, committing and pushing changes
3. Create PRs - All work is pushed and submitted as pull requests
4. Handle CI - Wait for checks, fix failures, address review comments
5. Merge - Auto-merge when approved (configurable)
6. Verify - Confirm all success criteria are met

Core Philosophy: Claude is smart enough to do the work AND verify it. Task Master keeps the loop going and persists state between sessions.

Workflow

┌─────────────────────────────────────────────────────────────────┐
│                         PLANNING                                 │
│  Read codebase → Create task list → Define success criteria     │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                      WORKING (per task)                          │
│  Make changes → Run tests → Commit → Push → Create PR           │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                       PR LIFECYCLE                               │
│  Wait for CI → Fix failures → Address reviews → Merge           │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                       VERIFICATION                               │
│  Run tests → Check lint → Verify criteria → Done                │
└─────────────────────────────────────────────────────────────────┘

Work Completion Requirements

Every task must be:

• Committed with a descriptive message
• Pushed to remote (git push -u origin HEAD)
• In a PR (gh pr create ...)

Work is NOT complete until it's pushed and in a pull request.

Installation

Prerequisites

1. Python 3.10+ - Install Python
2. Claude CLI - Install Claude and run claude to authenticate
3. GitHub CLI - Install gh and run gh auth login

Install Claude Task Master

Option 1: Using uv (recommended)

# Install uv if you haven't already
curl https://astral.sh/uv/install.sh | sh

# Install Claude Task Master
uv sync

# Verify installation
uv run claudetm doctor

Option 2: Using pip

# Install from PyPI
pip install claude-task-master

# Verify installation
claudetm doctor

Option 3: Development installation

# Clone the repository
git clone https://github.com/developerz-ai/claude-task-master
cd claude-task-master

# Install with development dependencies
pip install -e ".[dev]"

# Run tests
pytest

Initial Setup

Run the doctor command to verify everything is configured:

claudetm doctor

This checks for:

• ✓ Claude CLI credentials at ~/.claude/.credentials.json
• ✓ GitHub CLI authentication
• ✓ Git configuration
• ✓ Python version compatibility

Configuration

Claude Task Master uses a config file to override environment variables. This is useful for:

• Using alternative API providers (OpenRouter, etc.)
• Customizing model names
• Setting project-specific settings

Create Config File

# Initialize default config
claudetm --init-config

# View current config
claudetm --show-config

This creates .claude-task-master/config.json:

{
  "version": "1.0",
  "api": {
    "anthropic_api_key": null,
    "anthropic_base_url": "https://api.anthropic.com",
    "openrouter_api_key": null,
    "openrouter_base_url": "https://openrouter.ai/api/v1"
  },
  "models": {
    "sonnet": "claude-sonnet-4-5-20250929",
    "opus": "claude-opus-4-5-20251101",
    "haiku": "claude-haiku-4-5-20251001"
  },
  "git": {
    "target_branch": "main",
    "auto_push": true
  }
}

Environment Variables

The config file sets these environment variables before Python starts:

Config Key	Environment Variable	Description
api.anthropic_api_key	ANTHROPIC_API_KEY	Anthropic API key
api.anthropic_base_url	ANTHROPIC_BASE_URL	API base URL
api.openrouter_api_key	OPENROUTER_API_KEY	OpenRouter API key
api.openrouter_base_url	OPENROUTER_BASE_URL	OpenRouter base URL
models.sonnet	CLAUDETM_MODEL_SONNET	Model for sonnet tier
models.opus	CLAUDETM_MODEL_OPUS	Model for opus tier
models.haiku	CLAUDETM_MODEL_HAIKU	Model for haiku tier
git.target_branch	CLAUDETM_TARGET_BRANCH	Target branch for PRs

Using OpenRouter

To use OpenRouter instead of direct Anthropic API:

{
  "api": {
    "openrouter_api_key": "sk-or-v1-xxx",
    "openrouter_base_url": "https://openrouter.ai/api/v1"
  },
  "models": {
    "sonnet": "anthropic/claude-sonnet-4",
    "opus": "anthropic/claude-opus-4",
    "haiku": "anthropic/claude-haiku"
  }
}

Debug Config Loading

# Enable debug mode to see config loading
CLAUDETM_DEBUG=1 claudetm status

Usage

CLI Commands

Command	Description
claudetm start "goal"	Start a new task
claudetm resume	Resume a paused task
claudetm status	Show current status
claudetm plan	View task list
claudetm progress	View progress summary
claudetm context	View accumulated learnings
claudetm logs	View session logs
claudetm pr	Show PR status and CI checks
claudetm comments	Show review comments
claudetm clean	Clean up task state
claudetm doctor	Verify system setup

Start Options

claudetm start "Your goal here" [OPTIONS]

Option	Description	Default
--model	Model to use (sonnet, opus, haiku)	sonnet
--auto-merge/--no-auto-merge	Auto-merge PRs when ready	True
--max-sessions	Limit number of sessions	unlimited
--pause-on-pr	Pause after creating PR	False

Common Workflows

# Simple task with auto-merge
claudetm start "Add factorial function to utils.py with tests"

# Complex task with manual review
claudetm start "Refactor auth system" --model opus --no-auto-merge

# Limited sessions to prevent runaway
claudetm start "Fix bug in parser" --max-sessions 5

# Monitor progress
watch -n 5 'claudetm status'

Examples & Use Cases

Check the examples/ directory for detailed walkthroughs:

Quick Examples

# Add a simple function
claudetm start "Add a factorial function to utils.py with tests"

# Fix a bug
claudetm start "Fix authentication timeout in login.py" --no-auto-merge

# Feature development
claudetm start "Add dark mode toggle to settings" --model opus

# Refactoring
claudetm start "Refactor API client to use async/await" --max-sessions 5

# Documentation
claudetm start "Add API documentation and examples"

Available Guides

1. Basic Usage - Simple tasks and fundamentals
2. Feature Development - Building complete features
3. Bug Fixing - Debugging and fixing issues
4. Code Refactoring - Improving code structure
5. Testing - Adding test coverage
6. Documentation - Documentation and examples
7. CI/CD Integration - GitHub Actions workflows
8. Advanced Workflows - Complex scenarios

Troubleshooting

Credentials & Setup

"Claude CLI credentials not found"

# Run the Claude CLI to authenticate
claude

# Verify credentials were saved
ls -la ~/.claude/.credentials.json

# Run doctor to check setup
claudetm doctor

"GitHub CLI not authenticated"

# Authenticate with GitHub
gh auth login

# Verify authentication
gh auth status

Common Issues

Task appears stuck or not progressing

# Check current status
claudetm status

# View detailed logs
claudetm logs -n 100

# If truly stuck, you can interrupt and resume
# Press Ctrl+C, then:
claudetm resume

PR creation fails

# Verify you're in a git repository
git status

# Verify remote is set up
git remote -v

# Check if a PR already exists
gh pr list

# Run doctor to diagnose
claudetm doctor

Tests or linting failures

The system will handle failures and retry. To debug:

# Check the latest logs
claudetm logs

# View progress summary
claudetm progress

# See what Claude learned from errors
claudetm context

Clean up and restart

# Safe cleanup - removes state but keeps logs
claudetm clean

# Force cleanup without confirmation
claudetm clean -f

# Start fresh task
claudetm start "Your new goal"

Performance Tips

1. Use the right model:

   • opus for complex tasks (default)
   • sonnet for balanced speed/quality
   • haiku for simple tasks

2. Limit sessions to prevent infinite loops:

   claudetm start "Task" --max-sessions 10
   

3. Manual review for critical changes:

   claudetm start "Task" --no-auto-merge
   

4. Monitor in another terminal:

   watch -n 5 'claudetm status'
   

Debug Mode

View detailed execution information:

# Show recent log entries
claudetm logs -n 200

# View current plan and progress
claudetm plan
claudetm progress

# See accumulated context from previous sessions
claudetm context

Architecture

The system follows SOLID principles with strict Single Responsibility:

Core Components

Component	Responsibility
Credential Manager	OAuth credential loading from ~/.claude/.credentials.json
State Manager	Persistence to .claude-task-master/ directory
Agent Wrapper	Claude Agent SDK interactions with streaming output
Planner	Planning phase with read-only tools (Read, Glob, Grep, Bash)
Orchestrator	Main execution loop and workflow stage management
GitHub Client	PR creation, CI monitoring, comment handling
PR Cycle Manager	Full PR lifecycle (create → CI → reviews → merge)
Context Accumulator	Builds learnings across sessions

Workflow Stages

working → pr_created → waiting_ci → ci_failed → waiting_reviews → addressing_reviews → ready_to_merge → merged

Each stage has specific handlers that determine when to transition to the next stage.

State Directory

.claude-task-master/
├── goal.txt              # Original user goal
├── criteria.txt          # Success criteria
├── plan.md               # Task list with checkboxes
├── state.json            # Machine-readable state
├── progress.md           # Progress summary
├── context.md            # Accumulated learnings
└── logs/
    └── run-{timestamp}.txt    # Full log (kept on success)

Exit Codes

• 0 (Success): All tasks completed, criteria met. State cleaned up, logs preserved.
• 1 (Blocked): Task cannot proceed, needs human intervention or error occurred.
• 2 (Interrupted): User pressed Ctrl+C, state preserved for resume.

Development

Testing

pytest                    # Run all tests
pytest -v                 # Verbose output
pytest -k "test_name"     # Run specific tests

Linting & Formatting

ruff check .              # Lint
ruff format .             # Format
mypy .                    # Type check

License

MIT