ops-rotate-setup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ops-rotate-setup (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.
Load ops-rules before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If AskUserQuestion / Workflow are missing, follow Rule 10 in ops-rules (Hermes: numbered options / two-turn Telegram card; delegate_task).
Direct Claude browser, OAuth, magic-link, setup, and unattended authentication are disabled. Do not launch a browser, poll email, invoke rotate.mjs --setup, invoke rotate-magic.mjs, modify auth inventory, or suggest an environment bypass.
Tell the operator to use scripts/account-rotation/staged-enrollment.mjs with:
operation lock.
stage approval for an externally capturedCLIProxyAPI Claude auth candidate.
activate approval bound to the staged digest and attestingwritersQuiesced: true.
The attestation records operator confirmation; it does not stop services or contain writers itself. This skill does not sign approvals or perform either operation on the operator's behalf.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.