ponytail-review-gate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ponytail-review-gate (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 when installing, explaining, or applying the Ponytail review gate to a project.
Add this to a target repo's AGENTS.md:
For any task that writes, edits, refactors, scaffolds, or reviews code in this repo, use the `ponytail-adversarial-review` skill from the `ponytail-review-gate` plugin.
The completion gate is mandatory: run Ponytail adversarial review on the changed code, decide corrective actions, apply accepted fixes, and verify before finishing.git status --short and relevant diffs.ponytail-review against changed code only.Do not run ponytail-audit for ordinary per-diff completion. Reserve it for explicit whole-repo audit requests.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.