loop-worker — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited loop-worker (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.
Use /loop for in-session periodic workers. Cache-aware delays keep prompt cache warm:
min(270, cache_ttl * 0.9) -- default 270sDispatch a worker via MCP: mcp__claude-flow__hooks_worker-dispatch({ trigger: "WORKER_NAME" })
Then schedule the next iteration: ScheduleWakeup({ delaySeconds: 270, reason: "next WORKER_NAME iteration" })
| Worker | Interval | Description |
|---|---|---|
| audit | 270s | Security analysis |
| optimize | 270s | Performance optimization |
| consolidate | 600s | Memory consolidation |
| predict | 270s | Predictive preloading |
| map | 600s | Codebase mapping |
| testgaps | 270s | Test coverage analysis |
| document | 600s | Auto-documentation |
| benchmark | 600s | Performance benchmarking |
MCP tool responses include [LOOP_SUGGESTION] and [CRON_SUGGESTION] hints -- follow them.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.