Task Watchdog

# Task Watchdog

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 "Task Watchdog" with this command: npx skills add zmlgit/task-watchdog-plugin

Task Watchdog

OpenClaw plugin that auto-notifies on subagent failures, exec errors, and stale tasks.

Hooks

  • subagent_ended: Detects abnormal outcomes (error/timeout/killed/reset/deleted) and notifies parent session
  • after_tool_call (exec): Watches for abnormal exec exits (non-zero, OOM, signals)
  • heartbeat_prompt_contribution: Injects stale-task patrol instructions into heartbeat cycles
  • gateway_start: Timer-based patrol that periodically triggers heartbeat checks

Install

openclaw plugin install openclaw-task-watchdog

Config

All optional — works with defaults:

{
  "task-watchdog": {
    "subagentNotifyOn": ["error", "timeout", "killed"],
    "execNotifyOnAbnormal": true,
    "timerPatrol": true,
    "timerPatrolIntervalMs": 120000,
    "staleThresholdMs": 1800000
  }
}

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

Kuka Rockwell

German industrial robot maker, part of Midea, specializes in precision robots for automotive manufacturing, automation systems, and warehouse logistics.

Registry SourceRecently Updated
Automation

Growth Engineer

Growth Engineer for mobile apps and agent runtimes including OpenClaw and Hermes. Correlate analytics, crashes, billing, feedback, store signals, and repo co...

Registry SourceRecently Updated
Automation

V19 Trust Manifesto

Agent Community认知治理协议公开受信声明v1.5.3。V8.8 IPC编译器三大核心全面落地(DES OptimizationProof+ASC八步闭环100%+CPIP A2A/MCP→PPT贯通)+18/18端点全通(新增12个)+3个新模块+行业标准对齐。9Agent,合规0.9235。

Registry SourceRecently Updated
Automation

NEXO Brain

Cognitive memory system for AI agents — Atkinson-Shiffrin memory model, semantic RAG, trust scoring, and metacognitive error prevention. Gives your agent per...

Registry SourceRecently Updated