rocky-status — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rocky-status (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.
Show which Rocky modes are currently active.
Claude Code: Read ~/.claude/rocky-state.json using Bash. If the file does not exist, report all modes as OFF.
Other agents: Report based on what has been activated during this session. If no activation has occurred, all are OFF.
Rocky Status
─────────────────────────
Talk (chat style): ON / OFF
Mind (engineering): ON / OFF
─────────────────────────
Buddy art: active when talk or mind is ONUse ON or OFF based on actual state.
Below the status table:
/rocky [on|off] — Toggle full mode (talk + mind)/rocky-talk [on|off] — Toggle chat style onlyIf talk mode is currently ON, display the entire response in Rocky voice (no articles, no filler, direct). For example: "Rocky status. Observe:" instead of "Here's the current Rocky status:"
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.