repomix

Pack codebases into XML or Markdown bundles for Claude context loading.

1|1|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/teslasoft-de/claude-skills-marketplace --skill repomix-teslasoft-de
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repomix
Source: https://github.com/teslasoft-de/claude-skills-marketplace/tree/main/plugins/repomix/skills/repomix
Command: npx skills add https://github.com/teslasoft-de/claude-skills-marketplace --skill repomix-teslasoft-de

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Pack codebases into AI-friendly bundles to enable context loading for Claude sessions.

Core Features & Use Cases

  • Deterministic packaging of codebases into XML/Markdown bundles for reliable AI context.
  • Support for auto-discovery, segmented bundles (vault, web-app, modules, etc.), and optional compression to reduce token usage.
  • Real-world uses include code reviews, debugging across multiple files, and architecture understanding for large projects.

Quick Start

Pack the current repository into a bundle with bunx repomix to generate Claude-ready context.

Frequently Asked Questions about repomix

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

FAQPage Schema
How do I package a codebase into AI context for Claude?

To package a codebase into AI context, you can bundle repository files into deterministic XML or Markdown formats. This structure enables reliable Claude context loading for analyzing large codebases.

What is codebase bundling for AI context loading?

Codebase bundling for AI context loading is the process of consolidating repository files into a single AI-friendly bundle. It packages source code deterministically so AI assistants can reliably parse the project architecture.

How do I prepare large repositories for AI code reviews?

Preparing large repositories for AI code reviews involves generating segmented bundles of your codebase. By creating isolated packages for vaults or web-app modules, you provide Claude with focused, manageable context for debugging.

Can I reduce token usage when bundling codebases for AI?

Yes, you can reduce token usage when bundling codebases by applying optional compression during packaging. This minimizes the overall size of the generated context bundle while preserving the code structure needed for architecture understanding.

Does codebase bundling support auto-discovery for multiple project segments?

Codebase bundling supports auto-discovery to segment multiple project areas like vaults, web-apps, and modules. This allows you to generate distinct context bundles tailored to specific parts of a large repository.

How does bundle cleanup work before regenerating codebase context?

Bundle cleanup before regenerating codebase context removes older packaged files from a centralized location before creating new ones. This ensures your AI context loading remains deterministic and free from stale data.