Agent skill
self-heal-openclaw
Auto-recover OpenClaw when health goes offline, gateway token mismatch (1008) appears, Telegram stops replying, or browser/control-ui disconnects. Runs safe first-pass repair and optional deep cleanup.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/self-heal-openclaw
SKILL.md
Self-Heal OpenClaw
Use this skill when OpenClaw is unstable, for example:
health offlineorGateway not reachabletoken_mismatch/1008 unauthorized- Telegram channel is connected but no replies are sent
- Browser/Copilot shows disconnected while gateway should be local
Default action (safe repair)
Run:
bash scripts/self_heal_openclaw.sh --profile jarvis
This performs non-destructive recovery:
- Does not touch token/config by default (stability-first mode)
- Ensures LaunchAgent is installed
- Restarts only if health fails twice in a row (with 30-minute cooldown)
- Runs health and channel probe checks
If token mismatch is explicitly confirmed (1008 unauthorized), run:
bash scripts/self_heal_openclaw.sh --profile jarvis --sync-token
This additionally syncs:
gateway.remote.token<-gateway.auth.token$HOME/openclaw_pro/gateway.token
Deep cleanup (only when safe repair fails)
Run:
bash scripts/self_heal_openclaw.sh --profile jarvis --deep-clean
--deep-clean additionally removes stuck local session cache under:
~/.openclaw-jarvis/agents/main/sessions/*.jsonl~/.openclaw-jarvis/agents/main/sessions/sessions.json
After repair checklist
- Confirm
openclaw --profile jarvis healthis OK - Confirm
openclaw --profile jarvis channels status --probeis OK - If web still fails, re-enter token in Control UI from
$HOME/openclaw_pro/gateway.token
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?