How to Audit AGENTS.md and CLAUDE.md for Stale Instructions — Without Deleting Anything

说明与用途

Skill Sunset 对 AGENTS.md 和 CLAUDE.md 进行审计，识别过时、重复或冲突的规则，并生成安全、基于证据的清理计划和测试模板。

问题

AI coding agents’ instruction files grow over time, leading to stale, duplicate, or conflicting rules that are hard to clean up safely.

结果

The audit identifies 11 findings across 5 files, including 2 UPDATE, 1 DEMOTE, 1 RETIRE candidate, and 7 TEST hypotheses, enabling safe, evidence‑based cleanup.

工作流

• Run npx skill-sunset@latest audit --codex --open or --claude for a local audit
• Review the generated advisory report bundle
• For TEST findings, generate an experiment template with npx skill-sunset@latest test .skill-sunset/experiment-template.json --root .
• Run experiments only with --run and optionally --inherit-env
• Validate results, obtain human approval, then archive or edit the instruction
• Re‑audit to confirm changes
• Integrate with HOL Guard if desired

证据

The audit is local and read‑only. The core does not call an AI API, consume model quota, or read provider credentials.

来源

The deterministic findings include a broken local Markdown reference and a complete duplicate generic Skill bundle.

来源

For a TEST finding, Skill Sunset generates an experiment template.

来源