watchclaw
Auto-recovery watchdog for OpenClaw gateway. Monitors health, detects bad config changes, and recovers via git stash/revert. Supports native and Docker restart modes with pluggable alerts.
Why use this skill?
Install watchclaw to automatically recover your OpenClaw gateway from bad config changes. Supports git-based rollbacks, Docker, and polling.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jarvis4wang/watchclawWhat This Skill Does
watchclaw acts as a mission-critical safety net for your OpenClaw gateway. It is designed to mitigate downtime caused by unstable configuration changes. By continuously polling the gateway's HTTP health endpoint, it detects failures in real-time. When a failure is identified, it correlates the issue with your git repository status, distinguishing between uncommitted changes and bad commits. In the event of a crash or instability, it automatically triggers a recovery protocol—executing git stashes or reverts—before performing a service restart. Whether you are running locally in native mode or containerized via Docker, watchclaw ensures your gateway remains operational, providing peace of mind during iterative configuration development.
Installation
Ensure you have bash 4+, git, and curl installed on your host system. To install, use the OpenClaw CLI:
clawhub install openclaw/skills/skills/jarvis4wang/watchclaw
Once installed, copy the provided .conf.example file to your local directory, edit it to match your GATEWAY_PORT and GATEWAY_CONFIG_DIR, and ensure your OpenClaw configuration directory is initialized as a git repository. You can then trigger the watchdog using the standard CLI commands provided by the skill.
Use Cases
- Automated Gateway Reliability: Ideal for users who frequently tweak configuration files and want to avoid manual rollbacks after an accidental syntax error or invalid logic push.
- Production Stability: For gateways serving live traffic, watchclaw provides a 'probation' period for new configurations, ensuring only stable commits remain active.
- Container Management: Perfect for users running OpenClaw in Docker containers, as it simplifies the process of restarting services without manually interacting with the Docker daemon.
Example Prompts
- "OpenClaw, start the watchclaw daemon for my gateway on port 18790 in the background."
- "Check the current status and health of my gateway using the watchclaw monitoring system."
- "Follow the watchclaw logs to see why the latest configuration change caused a gateway restart."
Tips & Limitations
To get the most out of watchclaw, always ensure your configuration directory is a properly initialized git repository; otherwise, the auto-recovery features will be ineffective. Use the probation mode if you are making radical changes to prevent accidental cycles of restart-failure. Note that while this skill supports both native and Docker environments, it does require write access to your config directory to perform git operations. Finally, always test your alert hooks (like iMessage or webhooks) in a dev environment before relying on them for production, as network misconfigurations may delay failure notifications.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jarvis4wang-watchclaw": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, code-execution