repomix

Package local or remote repositories into single XML, Markdown, JSON, or Plain outputs.

10|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/samhvw8/dot-claude --skill repomix-samhvw8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/samhvw8/dot-claude/tree/main/skills/repomix
Command: npx skills add https://github.com/samhvw8/dot-claude --skill repomix-samhvw8

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires repomix, node, npm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Repomix packages entire repositories into AI-friendly single outputs to feed LLMs, simplifying context provisioning for Claude, ChatGPT, Gemini, and others.

Core Features & Use Cases

  • Repository Packaging: Output in multiple formats (XML/Markdown/JSON/Plain) with token counting
  • Remote Support: Package remote repos without cloning
  • Pattern & Security: Respect .gitignore, apply filtering, and perform basic security checks

Quick Start

Package current directory into a single XML output: repomix

Frequently Asked Questions about repomix

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I package a repository into a single file for LLM context?

Package repositories into AI-friendly single outputs using repomix, which bundles entire codebases into XML, Markdown, JSON, or plain text formats optimized for LLM ingestion without manual file selection or context loss.

Can I package remote repositories without cloning them locally?

Repomix supports remote repository packaging, allowing you to generate AI-ready context from GitHub, GitLab, or other remote sources directly without downloading or cloning the full repository first.

What output formats does repository packaging support?

Repository packaging outputs multiple formats—XML, Markdown, JSON, and plain text—each optimized for different LLM workflows, with built-in token counting to manage context window constraints.

Does repository packaging respect .gitignore patterns and security concerns?

Repomix respects .gitignore rules during packaging, applies pattern-based filtering, performs basic security checks, and optionally strips comments to reduce token overhead while protecting sensitive paths.

Can I use repository packaging across different programming languages?

Repository packaging works across languages and frameworks since it processes entire codebases structurally, making it suitable for polyglot projects, security audits, bug investigation, and AI-driven implementation planning regardless of language.