janitor-precheck — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited janitor-precheck (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.
Renamed in v1.3. Pre-install check is now part of /janitor-discover. Passing a GitHub URL or local path to /janitor-discover runs the same overlap analysis. This alias will be removed in v1.4.
When invoked, run /janitor-discover with the same argument and mention the rename in one short line at the top.
bash ~/.claude/skills/skills-janitor/scripts/discover.sh <github-url-or-path> [--json]Examples:
discover.sh https://github.com/user/my-skilldiscover.sh user/my-skilldiscover.sh ~/Downloads/some-skill//janitor-discover <url>/janitor-discover <path>The v1.3 check is more accurate than v1.2 because the installed-skills baseline now includes plugin-namespaced skills (marketing-skills:image, figma:figma-use, etc.) that v1.2 was blind to.
/janitor-discover — the new combined entry point/janitor-report — full health check, including existing duplicates~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.