🤖 Claude Code Starter Kit

A production-ready boilerplate for integrating Claude Code into your development workflow. Automate testing, security scanning, code review, and routine maintenance tasks.

📦 MCP Server

All commands and agents in this kit are also available as an MCP (Model Context Protocol) server, making them usable from Claude Desktop, Claude Code, or any MCP-compatible client.

Install

pip install claude-code-starter-kit-mcp

Setup in Claude Code

Add to your project's .claude/settings.json (or ~/.claude/settings.json for global use):

{
  "mcpServers": {
    "claude-code-starter-kit": {
      "command": "claude-code-starter-kit-mcp"
    }
  }
}

Setup in Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "claude-code-starter-kit": {
      "command": "claude-code-starter-kit-mcp"
    }
  }
}

Available MCP Tools

All tools accept an optional arguments string (e.g. a file path or flags like --changed).

PyPI Auto-publish

Releases to PyPI are automated via GitHub Actions. Push a version tag to trigger a publish:

git tag v0.2.0
git push origin v0.2.0

Requires a PyPI Trusted Publisher configured for the pypi environment in your repository settings.

🎯 What This Kit Provides

🚀 Quick Start

1. Copy to Your Project

# Clone this repo
git clone https://github.com/dachivadachkoria/claude-code-starter-kit.git

# Copy the .claude directory to your project
cp -r claude-code-starter-kit/.claude your-project/
cp claude-code-starter-kit/CLAUDE.md your-project/

2. Customize CLAUDE.md

Edit CLAUDE.md in your project root to match your:

• Tech stack

• Testing conventions

• Code style

• Project structure

3. Start Using

cd your-project
claude

# Now use the commands:
/test src/myfile.py           # Generate tests
/security-check                 # Check vulnerabilities
/detailed-review                        # Code review
/fix-bugs                      # Auto-fix common issues

📁 Repository Structure

.claude/
├── settings.json              # Claude Code configuration
├── commands/                  # Slash commands
│   ├── test.md               # /test - Generate unit tests
│   ├── test-coverage.md      # /test-coverage - Coverage analysis
│   ├── security-check.md      # /security-check - Vulnerability check
│   ├── detailed-review.md             # /detailed-review - Code review
│   ├── fix-bugs.md           # /fix-bugs - Auto-fix issues
│   ├── docs.md               # /docs - Generate documentation
│   └── refactor.md           # /refactor - Safe refactoring
├── agents/                    # Specialized AI agents
│   ├── test-engineer.md      # Testing specialist
│   ├── security-auditor.md   # Security expert
│   ├── code-reviewer.md      # Review specialist
│   └── bug-hunter.md         # Bug detection expert
└── knowledge-base/            # Project-specific guidelines
    ├── testing-guide.md
    └── security-checklist.md

CLAUDE.md                      # Project context (customize this!)
.github/
└── workflows/
    └── claude-review.yml      # Optional: CI integration

🔧 Available Commands

Testing Commands

Security Commands

Code Quality Commands

Documentation Commands

💡 Built-in Commands

Claude Code has excellent built-in commands you should know:

• /security-review - AI-powered security scanning

• /review - Code review

• /init - Initialize project with CLAUDE.md

• /compact - Compress context when running low

🛡️ Safety Guidelines

What Claude Code CAN Do Safely

✅ Generate and run tests
✅ Analyze code for vulnerabilities
✅ Suggest fixes with explanations
✅ Create documentation
✅ Refactor with your approval

What Requires Your Review

⚠️ Any changes to authentication/authorization
⚠️ Database migrations
⚠️ Environment/config changes
⚠️ Dependency updates
⚠️ Production deployment scripts

Best Practices

1. Review before commit - Always review generated code

2. Use branches - Let Claude work on feature branches

3. Incremental changes - Small, focused tasks work best

4. Test first - Run tests before accepting changes

5. Version control - Commit frequently, revert if needed

🔌 Language-Specific Setup

# Add to your CLAUDE.md

## Testing
- Framework: pytest
- Run: `pytest tests/ -v`
- Coverage: `pytest --cov=src --cov-report=html`

## Style
- Formatter: black, isort
- Linter: ruff or flake8
- Types: mypy

# Add to your CLAUDE.md

## Testing
- Framework: jest or vitest
- Run: `npm test`
- Coverage: `npm test -- --coverage`

## Style
- Formatter: prettier
- Linter: eslint
- Types: TypeScript strict mode

# Add to your CLAUDE.md

## Testing
- Framework: testing + testify
- Run: `go test ./...`
- Coverage: `go test -coverprofile=coverage.out ./...`

## Style
- Formatter: gofmt, goimports
- Linter: golangci-lint

🤝 Contributing

Contributions welcome! Please read CONTRIBUTING.md for guidelines.

Ideas for Contributions

• More language-specific templates

• Framework-specific commands (Django, React, etc.)

• CI/CD integration examples

• IDE extension recommendations

• Video tutorials

📚 Resources

• Claude Code Documentation

• Anthropic API Docs

📄 License

MIT License - feel free to use in personal and commercial projects.

Made with 🤖 by the community, for the community

Star ⭐ this repo if you find it useful!