optimize-agents-md — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited optimize-agents-md (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Improve AGENTS.md and scoped agent instruction files without weakening the repo's operational contract.
Use this skill when the user asks to:
Do not optimize by chasing a fixed token target. Preserve rules that encode repo-specific safety, validation, or workflow constraints even when they are verbose.
Before editing instructions, collect current evidence:
git log --oneline -20
git diff main...HEAD --stat
git log --oneline -- AGENTS.md
find .agents/skills -name 'SKILL.md' | sortWhen sources conflict, use the repo hierarchy:
src/ code and executable behaviorAGENTS.md by scopeUpdate stale prose rather than making code conform to stale docs.
gh for GitHub,conventional commits, scoped validation, directory boundaries, module naming, and skill-trigger guidance.
rg.area-aware validation.
AGENTS.mdAGENTS.mdrg -n "stale-term|removed-command|old-path" AGENTS.md docs skills src package.json
git log --oneline -- AGENTS.mdremove: stale, duplicated, or generic instructionmerge: repeated project-specific ruleclarify: correct rule that caused confusionadd: recent failure mode or missing project constraintdocs, skills, PR workflow, commit workflow, or validation policy.
git diff --check -- AGENTS.md
rg -n "removed-command|old-path" AGENTS.md docs skills src package.jsonFor docs-only instruction edits, executable validation is usually unnecessary. State that explicitly in the final response. If the edit changes scripts, skill contracts, schemas, or runtime guidance with executable effects, run the affected targeted tests.
Prefer compact, testable instructions:
**Commit messages** - Use conventional commits. For multi-line bodies, prefer
`git commit -F /tmp/message.txt`; keep body lines <=100 chars.Avoid vague compression:
Be concise and commit correctly.Use tables only when they make scanning easier. Long tables with dense prose are not an improvement.
Add or refine rules when a concrete failure occurs, such as:
Write the rule as an actionable constraint, not a diary entry. Include the verification command when one exists.
Report:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.