Repomix

{
  "description": "Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.",
  "references": {
    "files": [
      "references/configuration.md",
      "references/usage-patterns.md"
    ]
  },
  "content": "Repomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Claude, ChatGPT, and Gemini.\r\n\r\n\r\n### Check Installation\r\n```bash\r\nrepomix --version\r\n```\r\n\r\n### Install\r\n```bash\r\nnpm install -g repomix\r\n\r\nbrew install repomix\r\n```\r\n\r\n### Basic Usage\r\n```bash\r\nrepomix\r\n\r\nrepomix --style markdown\r\nrepomix --style json\r\n\r\nnpx repomix --remote owner/repo\r\n\r\n\r\n### Repository Packaging\r\n- AI-optimized formatting with clear separators\r\n- Multiple output formats: XML, Markdown, JSON, Plain text\r\n- Git-aware processing (respects .gitignore)\r\n- Token counting for LLM context management\r\n- Security checks for sensitive information\r\n\r\n### Remote Repository Support\r\nProcess remote repositories without cloning:\r\n```bash\r\nnpx repomix --remote yamadashy/repomix\r\n\r\nnpx repomix --remote https://github.com/owner/repo\r\n\r\n\r\n### Code Review Preparation\r\n```bash\r\nrepomix --include \"src/**/*.ts\" --remove-comments -o review.md --style markdown\r\n```\r\n\r\n### Security Audit\r\n```bash\r\nnpx repomix --remote vendor/library --style xml -o audit.xml\r\n```\r\n\r\n### Documentation Generation\r\n```bash\r\nrepomix --include \"src/**,docs/**,*.md\" --style markdown -o context.md\r\n```\r\n\r\n### Bug Investigation\r\n```bash\r\nrepomix --include \"src/auth/**,src/api/**\" -o debug-context.xml\r\n```\r\n\r\n### Implementation Planning\r\n```bash\r\n\r\n### File Selection\r\n```bash\r\nrepomix --include \"src/**/*.ts,*.md\"\r\n\r\nrepomix -i \"tests/**,*.test.js\"\r\n\r\nrepomix --no-gitignore\r\n```\r\n\r\n### Output Options\r\n```bash\r\nrepomix --style markdown  # or xml, json, plain\r\n\r\nrepomix -o output.md\r\n\r\nrepomix --remove-comments\r\n\r\nrepomix --copy\r\n```\r\n\r\n### Configuration\r\n```bash\r\nrepomix -c custom-config.json",
  "name": "repomix",
  "id": "repomix_mrgoonie",
  "sections": {
    "Quick Start": "repomix --include \"src/**/*.ts\" --remove-comments -o output.md\r\n```",
    "Reference Documentation": "For detailed information, see:\r\n- [Configuration Reference](./references/configuration.md) - Config files, include/exclude patterns, output formats, advanced options\r\n- [Usage Patterns](./references/usage-patterns.md) - AI analysis workflows, security audit preparation, documentation generation, library evaluation",
    "Token Management": "Repomix automatically counts tokens for individual files, total repository, and per-format output.\r\n\r\nTypical LLM context limits:\r\n- Claude Sonnet 4.5: ~200K tokens\r\n- GPT-4: ~128K tokens\r\n- GPT-3.5: ~16K tokens",
    "When to Use": "Use when:\r\n- Packaging codebases for AI analysis\r\n- Creating repository snapshots for LLM context\r\n- Analyzing third-party libraries\r\n- Preparing for security audits\r\n- Generating documentation context\r\n- Investigating bugs across large codebases\r\n- Creating AI-friendly code representations",
    "Implementation Workflow": "When user requests repository packaging:\r\n\r\n1. **Assess Requirements**\r\n   - Identify target repository (local/remote)\r\n   - Determine output format needed\r\n   - Check for sensitive data concerns\r\n\r\n2. **Configure Filters**\r\n   - Set include patterns for relevant files\r\n   - Add ignore patterns for unnecessary files\r\n   - Enable/disable comment removal\r\n\r\n3. **Execute Packaging**\r\n   - Run repomix with appropriate options\r\n   - Monitor token counts\r\n   - Verify security checks\r\n\r\n4. **Validate Output**\r\n   - Review generated file\r\n   - Confirm no sensitive data\r\n   - Check token limits for target LLM\r\n\r\n5. **Deliver Context**\r\n   - Provide packaged file to user\r\n   - Include token count summary\r\n   - Note any warnings or issues",
    "Security Considerations": "Repomix uses Secretlint to detect sensitive data (API keys, passwords, credentials, private keys, AWS secrets).\r\n\r\nBest practices:\r\n1. Always review output before sharing\r\n2. Use `.repomixignore` for sensitive files\r\n3. Enable security checks for unknown codebases\r\n4. Avoid packaging `.env` files\r\n5. Check for hardcoded credentials\r\n\r\nDisable security checks if needed:\r\n```bash\r\nrepomix --no-security-check\r\n```",
    "Common Use Cases": "repomix --remove-comments --copy\r\n```",
    "Core Capabilities": "npx repomix --remote https://github.com/owner/repo/commit/hash\r\n```\r\n\r\n### Comment Removal\r\nStrip comments from supported languages (HTML, CSS, JavaScript, TypeScript, Vue, Svelte, Python, PHP, Ruby, C, C#, Java, Go, Rust, Swift, Kotlin, Dart, Shell, YAML):\r\n```bash\r\nrepomix --remove-comments\r\n```",
    "Command Line Reference": "repomix --init  # creates repomix.config.json\r\n```",
    "Additional Resources": "- GitHub: https://github.com/yamadashy/repomix\r\n- Documentation: https://repomix.com/guide/\r\n- MCP Server: Available for AI assistant integration"
  }
}

---
name: repomix
description: Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
---

# Repomix Skill

Repomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Claude, ChatGPT, and Gemini.

## When to Use

Use when:
- Packaging codebases for AI analysis
- Creating repository snapshots for LLM context
- Analyzing third-party libraries
- Preparing for security audits
- Generating documentation context
- Investigating bugs across large codebases
- Creating AI-friendly code representations

## Quick Start

### Check Installation
```bash
repomix --version
```

### Install
```bash
# npm
npm install -g repomix

# Homebrew (macOS/Linux)
brew install repomix
```

### Basic Usage
```bash
# Package current directory (generates repomix-output.xml)
repomix

# Specify output format
repomix --style markdown
repomix --style json

# Package remote repository
npx repomix --remote owner/repo

# Custom output with filters
repomix --include "src/**/*.ts" --remove-comments -o output.md
```

## Core Capabilities

### Repository Packaging
- AI-optimized formatting with clear separators
- Multiple output formats: XML, Markdown, JSON, Plain text
- Git-aware processing (respects .gitignore)
- Token counting for LLM context management
- Security checks for sensitive information

### Remote Repository Support
Process remote repositories without cloning:
```bash
# Shorthand
npx repomix --remote yamadashy/repomix

# Full URL
npx repomix --remote https://github.com/owner/repo

# Specific commit
npx repomix --remote https://github.com/owner/repo/commit/hash
```

### Comment Removal
Strip comments from supported languages (HTML, CSS, JavaScript, TypeScript, Vue, Svelte, Python, PHP, Ruby, C, C#, Java, Go, Rust, Swift, Kotlin, Dart, Shell, YAML):
```bash
repomix --remove-comments
```

## Common Use Cases

### Code Review Preparation
```bash
# Package feature branch for AI review
repomix --include "src/**/*.ts" --remove-comments -o review.md --style markdown
```

### Security Audit
```bash
# Package third-party library
npx repomix --remote vendor/library --style xml -o audit.xml
```

### Documentation Generation
```bash
# Package with docs and code
repomix --include "src/**,docs/**,*.md" --style markdown -o context.md
```

### Bug Investigation
```bash
# Package specific modules
repomix --include "src/auth/**,src/api/**" -o debug-context.xml
```

### Implementation Planning
```bash
# Full codebase context
repomix --remove-comments --copy
```

## Command Line Reference

### File Selection
```bash
# Include specific patterns
repomix --include "src/**/*.ts,*.md"

# Ignore additional patterns
repomix -i "tests/**,*.test.js"

# Disable .gitignore rules
repomix --no-gitignore
```

### Output Options
```bash
# Output format
repomix --style markdown  # or xml, json, plain

# Output file path
repomix -o output.md

# Remove comments
repomix --remove-comments

# Copy to clipboard
repomix --copy
```

### Configuration
```bash
# Use custom config file
repomix -c custom-config.json

# Initialize new config
repomix --init  # creates repomix.config.json
```

## Token Management

Repomix automatically counts tokens for individual files, total repository, and per-format output.

Typical LLM context limits:
- Claude Sonnet 4.5: ~200K tokens
- GPT-4: ~128K tokens
- GPT-3.5: ~16K tokens

## Security Considerations

Repomix uses Secretlint to detect sensitive data (API keys, passwords, credentials, private keys, AWS secrets).

Best practices:
1. Always review output before sharing
2. Use `.repomixignore` for sensitive files
3. Enable security checks for unknown codebases
4. Avoid packaging `.env` files
5. Check for hardcoded credentials

Disable security checks if needed:
```bash
repomix --no-security-check
```

## Implementation Workflow

When user requests repository packaging:

1. **Assess Requirements**
   - Identify target repository (local/remote)
   - Determine output format needed
   - Check for sensitive data concerns

2. **Configure Filters**
   - Set include patterns for relevant files
   - Add ignore patterns for unnecessary files
   - Enable/disable comment removal

3. **Execute Packaging**
   - Run repomix with appropriate options
   - Monitor token counts
   - Verify security checks

4. **Validate Output**
   - Review generated file
   - Confirm no sensitive data
   - Check token limits for target LLM

5. **Deliver Context**
   - Provide packaged file to user
   - Include token count summary
   - Note any warnings or issues

## Reference Documentation

For detailed information, see:
- [Configuration Reference](./references/configuration.md) - Config files, include/exclude patterns, output formats, advanced options
- [Usage Patterns](./references/usage-patterns.md) - AI analysis workflows, security audit preparation, documentation generation, library evaluation

## Additional Resources

- GitHub: https://github.com/yamadashy/repomix
- Documentation: https://repomix.com/guide/
- MCP Server: Available for AI assistant integration