repomix

Package repositories into AI-friendly single-file representations in XML, Markdown, JSON, or Plain text.

Updated Jul 23, 2025
One-click install
npx skills add https://github.com/levanminhduc/LuongHoaThoNew --skill repomix-levanminhduc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/levanminhduc/LuongHoaThoNew/tree/main/.claude/skills/repomix
Command: npx skills add https://github.com/levanminhduc/LuongHoaThoNew --skill repomix-levanminhduc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill packages entire repositories into AI-friendly files, enabling efficient ingestion by LLMs for analysis, planning, and audits.

Core Features & Use Cases

  • Repository Packaging: Produce AI-friendly representations with separators and multiple formats.
  • Git-aware processing: Respect .gitignore rules during packaging.
  • Remote support: Package remote repositories without cloning.

Quick Start

Package a local repository into repomix-output.xml and review the structure.

Frequently Asked Questions about repomix

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

FAQPage Schema
How do I prepare a repository for analysis by an LLM?

Package your repository into a single AI-friendly file using repomix, which converts your codebase into structured formats (XML, Markdown, JSON, or plain text) with clear separators and token counts so LLMs can ingest and analyze the full context efficiently.

Can I package a remote repository without cloning it locally?

Yes, repomix supports remote repository packaging, allowing you to generate AI-ready representations directly from remote sources without downloading the entire repository to your machine first.

Does the packaging process respect .gitignore rules?

Yes, repomix is Git-aware and respects .gitignore rules during packaging, ensuring that ignored files and directories are excluded from the AI-ready output automatically.

What output formats does repository packaging support?

Repomix generates repository snapshots in multiple formats—XML, Markdown, JSON, and plain text—with AI-optimized formatting and separators so you can choose the format best suited for your LLM or analysis tool.

How do I manage token limits when packaging large codebases?

Repomix includes token counting functionality to help you track context size, and supports optional comment removal to reduce token overhead when preparing repositories for LLM analysis under strict context constraints.

Can I use repository packaging for security audits and bug investigations?

Yes, repomix is designed for multiple use cases including security audits, bug investigations, third-party library analyses, and implementation planning across large codebases by providing complete, AI-readable repository context.