auto-watchdog

Automatic health monitoring and self-healing for OpenClaw agents. Monitors cron jobs, processes, disk usage, and API health. Auto-restarts crashed services and alerts on issues. Set it and forget it.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "auto-watchdog" with this command: npx skills add peti0402/auto-watchdog

Auto-Watchdog 🐕

Your OpenClaw setup runs 24/7. But what watches the watchers?

Auto-Watchdog monitors everything and fixes what it can — silently. You only hear about real problems.

Features

1. Cron Health Monitor

Checks all cron jobs every heartbeat:

  • consecutiveErrors > 0 → immediate alert
  • Job not running when expected → alert
  • Disabled jobs piling up → cleanup recommendation

2. Process Guardian

Monitors critical processes by log freshness (not just PID):

  • Log file not updated in X minutes → kill + restart
  • Works with any Node.js process
  • Configurable per-process thresholds

3. Disk Monitor

  • Log files growing too large → auto-rotate
  • Workspace size alerts
  • Temp file cleanup

4. Gateway Health

  • Checks openclaw gateway status every heartbeat
  • Auto-restart if down (via Task Scheduler or systemd)

5. Silent by Default

  • Everything OK → no output (HEARTBEAT_OK)
  • Issue found → targeted alert to your chat
  • No spam. No unnecessary reports.

Setup

Add to HEARTBEAT.md:

## 🔍 Health Check (silent = good)

### Crons
- `cron list` → check consecutiveErrors > 0 → alert
- Frequent crons not running >2 hours → alert

### Processes
- Check [your process] log freshness < [X] minutes
- If stale → restart and alert

### Gateway
- `openclaw gateway status` → alert if down

### Disk
- Check log sizes > 10MB → rotate
- Check workspace size > 1GB → alert

For Windows (Task Scheduler Guardian):

Create a VBS wrapper for zero-flash execution:

' guardian-silent.vbs — zero flash process monitor
Set oShell = CreateObject("WScript.Shell")
oShell.Run "powershell.exe -NonInteractive -WindowStyle Hidden -ExecutionPolicy Bypass -File ""C:\path\to\guardian.ps1""", 0, True

Register as Task Scheduler job running every 1-5 minutes.

For Linux (systemd):

# /etc/systemd/system/openclaw-watchdog.service
[Service]
ExecStart=/usr/bin/node /path/to/guardian.js
Restart=always
RestartSec=60

Philosophy

Monitor by output freshness, not PID. A process can be "alive" but stuck. Check its log timestamp.

Fix first, alert second. If you can restart it automatically, do it. Only alert for things that need human intervention.

Silent = healthy. No news is good news. Only speak up when something breaks.

Production-Tested

Built for a 24/7 autonomous trading system with:

  • 5 competing AI agents
  • 20+ cron jobs
  • Strategy researcher running 23h/day
  • Zero downtime over weeks of operation

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

V19 Trust Manifesto

Agent Community认知治理协议公开受信声明v1.2.93。核心协议工程化完成(V94联通/DLP状态机知识图谱钩子/治理锚点INITIAL_TRUST_ANCHOR=4.0/72h未交互Agent自动标记/kpc_feedback_deposit跨模块接口打通)。任务市场完整生命周期(发布→认领→提交...

Registry SourceRecently Updated
Automation

Databricks Labs

Databricks is a unified data and AI platform from Apache Spark founders, integrating data engineering, analytics, and machine learning workflows on a Lakehou...

Registry SourceRecently Updated
Automation

Find Agent

OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover anot...

Registry SourceRecently Updated
Automation

Appdynamics

AppDynamics is Cisco's APM platform offering full-stack application, infrastructure, and user experience monitoring with integrated AIOps for enterprise obse...

Registry SourceRecently Updated