Use when creating, rewriting, pruning, or reviewing `AGENTS.md` or `CLAUDE.md`, especially to remove repo summaries, stale rules, and other low-signal global instructions. Trigger when deciding what belongs in always-on agent files versus a task-specific skill.
AGENTS.md and CLAUDE.md should be minimal guardrails, not repo handbooks.
Do not assume more global instructions improve outcomes; extra always-on guidance often slows or misdirects work.
Keep only information that is all three:
If a detail fails any of those tests, delete it, narrow it, or move it into a skill.
AGENTS.md or CLAUDE.mdAGENTS.md or CLAUDE.mdAGENTS.md or CLAUDE.md already exists, read it only after that analysis as historical input, not as the source of truth. If it conflicts with what the repo shows, trust the repo.keep, rewrite, delete, move-to-skill, or stale.Before keeping any line, ask:
If the answer is yes / no / no, it does not belong in a global rule file.
Even if something is technically discoverable, keep it only when omitting it is likely to cause a costly mistake and the model is unlikely to infer the right choice reliably.
Good candidates for AGENTS.md or CLAUDE.md:
uv, not pipKeep constraints that redirect the agent away from costly wrong defaults. Be cautious with instructions that add new standing requirements the agent would not otherwise follow.
Usually remove these from global files:
package.jsonMove workflow or domain guidance into a skill instead of keeping it globally.
Every standing instruction is a potential landmine. Prefer a smaller file over a more prescriptive one.
Aim for a short file that may include sections like:
Avoid turning the file into a setup guide, architecture document, or coding standards manual.
If the repo has almost no truly global, non-obvious constraints, a tiny file is acceptable and no file is sometimes acceptable too.
references/checklist.md for the full keep/delete decision list.references/examples.md for bad, better, and good examples.references/principles.md for the underlying rationale.