go — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited go (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.
Thin alias over the atomic skills. Invoke each by name, in order, and continue automatically between steps — none of them is a stopping point. On any unrecoverable failure (a skill exhausts its 3-strike loop), stop and report; never bypass a failure to make closure appear to succeed.
Two standing rules: after every skill returns, restate position ("→ Returning to /go: next is step N (<name>)"); after any auto-compaction, re-invoke the skill governing the current step.
Goal: set a session goal now (SlashCommand /goal if available, otherwise state it and treat it as binding): "Current working tree landed as a PR — verify, preflight, and E2E green; PR URL returned."
Not for: mid-refactor trees, unrelated-changes trees (ask to scope down), draft/exploration work, or release-please-* branches.
code. Full stack-detected gates with its autonomous fix loop.verify once, then continue.pr skill branches in step 5.→ After step 5, suggest /babysit-pr <PR#> (or /loop 5m /babysit-pr <PR#>) to drive it to merge.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.