ooocooc

Open Skill Sunset — Security skill for Claude Code

Security community

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

How to install Open Skill Sunset

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

What Open Skill Sunset does

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Alternatives in Security

Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
Pareto Mac — by ParetoSecurity - Serves as development guide for Mac security audit tool with build instructions, contribut 431 ★

README

Skill Sunset

[![CI](https://github.com/ooocooc/open-skill-sunset/actions/workflows/ci.yml/badge.svg)](https://github.com/ooocooc/open-skill-sunset/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/skill-sunset.svg)](https://www.npmjs.com/package/skill-sunset) [![npm downloads](https://img.shields.io/npm/dm/skill-sunset.svg)](https://www.npmjs.com/package/skill-sunset) [![license](https://img.shields.io/github/license/ooocooc/open-skill-sunset.svg)](LICENSE)

[English](README.md) | [简体中文](README.zh-CN.md)

Your `AGENTS.md` only grows. Which rules are still earning their context?

Skill Sunset is a local, read-only retirement audit for `AGENTS.md`, `CLAUDE.md`, and generic `SKILL.md` instructions. It separates verified breakage and duplicates from unproven “this rule is obsolete” hypotheses. `TEST` is not `RETIRE`.

npx skill-sunset@latest audit --codex --open

No global installation is required. No source edits. No AI API. No model quota. No provider credentials.

**Third-party integration:** [HOL Guard v3.0.18](https://github.com/hashgraph-online/hol-guard/releases/tag/v3.0.18) includes a command-safety extension for the installed `skill-sunset audit` surface. [View the merged integration](https://github.com/hashgraph-online/hol-guard/pull/2611).

If Skill Sunset saves you one risky cleanup pass, [star the repository](https://github.com/ooocooc/open-skill-sunset). If a verdict is wrong, [share a redacted counterexample](https://github.com/ooocooc/open-skill-sunset/issues/new?template=false-positive.yml).

![A real Skill Sunset report generated from the repository test fixture](https://raw.githubusercontent.com/ooocooc/open-skill-sunset/main/docs/assets/skill-sunset-report.png)

The screenshot comes from a real report generated by the current CLI from `test/fixtures/sample-setup`: 5 files scanned, 11 findings, with duplicate retirement, stale-reference updates, progressive disclosure, and behavior hypotheses shown separately. [Op