repomix

Packages code repositories into XML, Markdown, or JSON files for LLM context preparation.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/toanalien/ezdevsecops --skill repomix-toanalien
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/toanalien/ezdevsecops/tree/main/.opencode/skills/repomix
Command: npx skills add https://github.com/toanalien/ezdevsecops --skill repomix-toanalien

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of preparing entire code repositories or specific parts of them into a single, AI-friendly file format, making them easily digestible for Large Language Models (LLMs).

Core Features & Use Cases

  • Repository Packaging: Converts codebases into AI-optimized formats (XML, Markdown, JSON, Plain text).
  • LLM Context Preparation: Ideal for feeding codebases to LLMs for analysis, review, or documentation.
  • Security Audits: Helps in packaging code for security analysis by identifying sensitive data.
  • Use Case: You need to provide a large codebase to an AI assistant for a security audit. Use Repomix to package the entire repository into a single XML file, ensuring sensitive information is flagged and comments are removed to reduce token count.

Quick Start

Use repomix to package the current directory into a markdown file.

Frequently Asked Questions about repomix

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

FAQPage Schema
How do I package a code repository for AI analysis?

Packaging a code repository for AI analysis involves converting the codebase into XML, Markdown, JSON, or plain text formats. This process creates a single AI-friendly file, making it easily digestible for LLMs during context preparation.

What is the best way to prepare a codebase snapshot for LLM context?

Preparing a codebase snapshot for LLM context is best achieved by packaging the repository into a single AI-optimized file. This approach ensures the entire codebase is structured effectively for large language model ingestion and review.

Can I run a security audit on a codebase by packaging it for LLMs?

You can perform a security audit by packaging the codebase for LLMs. The packaging process identifies sensitive data and can remove comments, ensuring the AI assistant receives a secure, token-optimized repository snapshot for analysis.

Does repository packaging support remote repositories and comment removal?

Repository packaging supports remote repository processing and comment removal. These features facilitate third-party library analysis and reduce token count by stripping unnecessary comments from the generated codebase snapshot.

What file formats are supported when packaging code for LLM preparation?

Packaging code for LLM preparation supports XML, Markdown, JSON, and plain text file formats. Converting the codebase into these AI-friendly formats allows flexible integration depending on your specific AI assistant requirements.