OpenClaw Healthcheck Cron
v1.0.0Create and run a reusable OpenClaw deep healthcheck automation using a cron job plus a script. Use when setting up scheduled OpenClaw health audits, standard...
⭐ 0· 985·3 current·4 all-time
byPedro Gonzalez@plgonzalezrx8
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match the included files and behavior: the script runs local OpenClaw checks (command -v openclaw, openclaw gateway status, openclaw status) and writes read-only artifacts under /tmp. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
SKILL.md stays on-topic: it instructs creating a cron agentTurn that executes bash scripts/healthcheck.sh, writing artifacts to a local output dir, and sanitizing local identifiers. One notable point: the example cron payload uses delivery.mode 'announce' — depending on your platform, that may cause the agent to broadcast the summary outside the host (e.g., into dashboards or notifications). Verify what 'announce' does in your environment before enabling automatic runs. Otherwise the script does not read other system files or network endpoints.
Install Mechanism
No install spec; skill is instruction-only with a small helper script. Nothing is downloaded or written outside the artifact directory (/tmp) created at runtime.
Credentials
No required env vars, credentials, or config paths are declared. The script optionally respects HEALTHCHECK_OUTPUT_DIR, HEALTHCHECK_EXCLUDE, and OPENCLAW_HEALTH_TZ environment variables as documented — these are reasonable and proportional.
Persistence & Privilege
always is false and the skill is user-invocable. The skill doesn't request persistent system-wide changes or access to other skills' configs. It writes only to its own artifact directory under /tmp.
Assessment
This appears to do what it claims: run local OpenClaw checks and write a summary to /tmp. Before installing: 1) Review how your platform handles delivery.mode 'announce' (it may publish results to dashboards/notifications). If you don't want external announcements, use 'none' or handle reporting inside the script. 2) Fix the script logic bug: failures increment 'warn' but the 'fail' counter is never increased, so 'NEEDS_ATTENTION' will never be produced; adjust check_cmd to increment fail when appropriate. 3) Confirm file permissions and retention for /tmp/openclaw-healthcheck (sensitive logs may be written there), and sanitize any outputs as SKILL.md suggests. 4) Run the script manually and verify output format before scheduling. If you require higher assurance, request provenance for the skill (author/homepage) and test in an isolated environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk97a2zsh003pph448ks043bjzh81d377
License
MIT-0
Free to use, modify, and redistribute. No attribution required.