ponytail-adversarial-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ponytail-adversarial-review (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.
Use this skill as a completion gate for code changes in a target repo. The main agent may write code normally, but it cannot finish until Ponytail has challenged the diff and the main agent has either fixed or explicitly declined each finding.
Use the vendored Ponytail skills in this plugin:
../ponytail/SKILL.md../ponytail-review/SKILL.md../ponytail-audit/SKILL.mdIf those paths are missing, fall back to the installed @ponytail and @ponytail-review skills if available. If neither is available, perform the same review manually using Ponytail's ladder: YAGNI, stdlib, native platform features, installed dependency, one line, then minimum code.
git status --short.git diff -- <changed tracked files>.ponytail-review to the changed code.ponytail-audit for ordinary per-diff completion; reserve it for explicit whole-repo audit requests.file:L<line>: <tag>: <what>. <replacement>.accept, reject, or defer.npm run lint, unit tests, typecheck, or an Expo health check.Keep the final concise. Include:
Lean already. Ship. or the accepted/rejected corrective actions.Do not paste a long review transcript unless the user asks for it.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.