operations-on-ci — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited operations-on-ci (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.
CI loop starts immediately after PR creation or after fix-and-recommit. CI loop is a separate task from PR creation. Do not skip.
step1 = get latest commit sha: gh pr view {pr} -R {owner}/{repo} --json headRefOid --jq '.headRefOid' step2 = wait for all check-runs to complete: Prefer webhook over polling. if mcp__github-webhook-mcp available: poll get_pending_status every 60 seconds on check_run pending: list_pending_events -> get_event for check_run events -> verify sha match -> mark_processed collect conclusions until no in-flight check-runs remain else: gh api repos/{owner}/{repo}/commits/{sha}/check-runs --jq '.check_runs[] | {name,status,conclusion}' repeat with sleep until: all status=="completed" step3 = conclusion judgment (refs #460): CI fail = any conclusion=="failure" CI pass = all conclusion in [success, skipped, neutral] CI pass -> proceed to [PR Review]. CI fail -> fix and recommit (restart CI loop from step1). CI loop safety (ref: Li+core.md#Loop Safety task/debug threshold): If still failing = externalize to issue comment, escalate to human.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.