safety-checks
Verify before you trust — model pinning, fallbacks, and runtime safety validation.
Setup & Installation
Install command
clawhub install leegitw/safety-checksIf the CLI is not installed:
Install command
npx clawhub@latest install leegitw/safety-checksOr install with OpenClaw CLI:
Install command
openclaw skills install leegitw/safety-checksor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/leegitw/safety-checksWhat This Skill Does
Runtime safety verification suite that consolidates model version pinning, fallback chain validation, cache staleness detection, and cross-session state checks. All operations are local file and metadata reads with no external API calls or data transmission. Consolidates four separate skills into a single aliased command.
Replaces four separate skill invocations with a single aliased suite that integrates directly with HEARTBEAT for automated periodic verification.
When to Use It
- Catching model version drift before a scheduled agent run
- Verifying fallback config entries exist after modifying agent settings
- Clearing stale cache entries during periodic workspace maintenance
- Detecting orphaned lock files left by a previously crashed session
- Running automated pre-flight safety checks on every session start via HEARTBEAT
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Catching model version drift before a scheduled agent run
- 1Catching model version drift before a scheduled agent run
- 2Verifying fallback config entries exist after modifying agent settings
- 3Clearing stale cache entries during periodic workspace maintenance
- 4Detecting orphaned lock files left by a previously crashed session
- 5Running automated pre-flight safety checks on every session start via HEARTBEAT
Verify before you trust — model pinning, fallbacks, and runtime safety validation.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.