ops-rotate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ops-rotate (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.
/ops:accounts)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).
This skill is a compat alias. Route all work through ops-accounts:
| Old verb | New |
|---|---|
| (none) / status | ops-accounts status (Claude section) |
| rotate-now | ops-accounts switch claude / ops-accounts rotate-now |
| list | ops-accounts list |
| add-account | ops-accounts setup claude |
| reauth | ops-accounts reauth claude <email> |
| pooled seats | CLIProxyAPI — see /ops:ops-fleet |
Load `skills/ops-accounts/SKILL.md` first, then for Claude-only depth use the bin:
"${CLAUDE_PLUGIN_ROOT}/bin/ops-accounts" status
"${CLAUDE_PLUGIN_ROOT}/bin/ops-accounts" rotate-now
"${CLAUDE_PLUGIN_ROOT}/bin/ops-accounts" reauth claude <email>Multi-provider status, Grok, Codex, Factory, Cursor: `/ops:accounts` only.
Vision: docs/ops/OPS-ACCOUNTS-VISION.md.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.