Package code repositories into single XML, Markdown, JSON, or plain text files.
npx skills add https://github.com/HsnSaboor/open-engineer --skill repomix-hsnsaboor
Please help me install this Agent Skill. Skill: repomix Source: https://github.com/HsnSaboor/open-engineer/tree/main/src/skills/bundled/samhvw8-repomix Command: npx skills add https://github.com/HsnSaboor/open-engineer --skill repomix-hsnsaboor
This Skill streamlines the process of preparing entire code repositories for analysis by Large Language Models (LLMs), making it easier to feed complex codebases into AI tools.
Use repomix to package the current directory into a markdown file named 'repo-context.md'.
High-intent search queries and answers about installing and using this skill.
To package a code repository for AI analysis, you can use a tool to consolidate local or remote codebases into a single file. This process aggregates all relevant code and configurations into formats like XML, Markdown, JSON, or plain text optimized for LLM consumption.
The best way to provide a large project for an AI security audit is to package the entire codebase into a single Markdown file. This ensures all relevant code and configurations are included and formatted specifically for AI consumption and context generation.
Yes, you can count tokens when preparing a codebase snapshot for an LLM. The packaging process includes token counting features to help you measure and manage the context size before passing the aggregated repository file to AI assistants.
Repository packaging for AI context generation supports both local and remote repositories. You can aggregate code from remote sources directly into AI-friendly files without needing to manually clone and traverse the entire project structure first.
Available output formats for converting a codebase include XML, Markdown, JSON, and plain text. These formats are designed to be AI-friendly, allowing LLMs like Claude, ChatGPT, and Gemini to easily parse and analyze the packaged code.
Removing comments when packaging code for LLM context generation reduces file size and token count, ensuring the AI focuses strictly on the executable code. This streamlines the input for security audits and complex codebase analysis.
parisgroup-aiSync shared skill directories from a remote Git repository into local Claude Code and Codex skill folders.
VoDaiLoczPackage entire code repositories into XML, Markdown, JSON, and plain text files.
mscipioMonitor AI model context window usage and warn before token overflow.
Khoatran1999Package entire code repositories into AI-friendly XML, Markdown, JSON, or plain text files.
