ops — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ops (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.
This is the single broad discovery entry for the OPS plugin. Specialist skill and agent bodies are intentionally absent from startup context.
$ARGUMENTS is empty, invoke the ops:ops-dash skill.Skill tool using its exact namespaced name:ops:<skill-name>. Forward the user's original arguments and intent unchanged.
would materially change an external action.
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).
Do not reproduce or summarize a specialist workflow from the index. Invoke the specialist so Claude Code loads its full body, allowed tools, effort, hooks, and turn budget on demand. Never invoke ops:ops from this router; that would recurse.
The capability index is routing metadata, not authority to perform an action. All approval, secrets, outbound-message, destructive-operation, and worktree gates remain owned by the selected specialist and the global hooks.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.