Asixa

Codemap Skill β€” AI skill for Claude Code

AI community

🧹 A code janitor for AI agents β€” map any codebase into functional modules, score every module 0-100 for tech debt, and clean up the spaghetti incrementally.

How to install Codemap Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Asixa/codemap-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Codemap Skill does

🧹 A code janitor for AI agents β€” map any codebase into functional modules, score every module 0-100 for tech debt, and clean up the spaghetti incrementally. A Claude Code / Codex skill.

Alternatives in AI

  • Agent Rules Books β€” AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code 2.6k β˜…
  • 09 Query Engine β€” Prompt 09: Get the QueryEngine (Core LLM Loop) Functional 2.3k β˜…
  • LiveAgent β€” A fully functional AI Agent desktop client that supports Webui access and can be creatively customized and exp 1.9k β˜…

README

🧹 codemap

**A code janitor for AI coding agents.** Point it at any repo and it draws an **interactive architecture map**, scores **every module 0–100** for technical debt, and helps you **pay down the cruft** β€” incrementally, one commit at a time.

![Claude Code skill](https://img.shields.io/badge/Claude%20Code-skill-f59e0b) ![Agent Skill](https://img.shields.io/badge/Agent%20Skill-Claude%20Β·%20Codex%20Β·%20Cursor-7c8794) ![Python 3 Β· stdlib only](https://img.shields.io/badge/python-3%20Β·%20stdlib%20only-3776ab) ![language agnostic](https://img.shields.io/badge/langs-Py%20Β·%20TS%20Β·%20Rust%20Β·%20C%23%20Β·%20C%2B%2B-555) ![license MIT](https://img.shields.io/badge/license-MIT-blue) [![tests](https://github.com/Asixa/codemap-skill/actions/workflows/test.yml/badge.svg)](https://github.com/Asixa/codemap-skill/actions/workflows/test.yml)

Every codebase accumulates cruft over time β€” monkeypatches, silent fallbacks, dead "legacy" paths, half-finished stubs, copy-pasted duplication, god-files, and valueless glue. **codemap surfaces that rot, ranks it, and hands an AI agent a clear punch-list to fix it** β€” with a regression-gated fix loop: a change is accepted only when an independent check shows your tests still pass.

![architecture map](examples/01-map.png)


Install

codemap follows the open **Agent Skills** standard (a folder with a `SKILL.md`), now shared by **Claude Code, Codex, and Cursor**. Clone it into the tool's `skills/` folder and it auto-discovers as **`/codemap`** β€” no extra config:

# Claude Code β€” global skills folder
git clone https://github.com/Asixa/codemap-skill ~/.claude/skills/codemap

# OpenAI Codex β€” global skills folder
git clone https://github.com/Asixa/codemap-skill ~/.codex/skills/codemap

# Cursor β€” global skills folder
git clone https://github.com/Asixa/codemap-skill ~/.cursor/skills/codemap

Restart the tool (or start a new session) and type **`/codemap`**. All three also accept a **per-project** install β€” drop