system-watchdog
System resource monitoring that detects wasteful or suspicious processes. Outputs structured JSON for any consumer.
How do I install this agent skill?
npx skills add https://github.com/tychohq/agent-skills --skill system-watchdogIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill monitors macOS system resources and processes. It captures full command-line arguments which may contain sensitive data and presents an indirect prompt injection surface by processing untrusted process data without sanitization.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
- Runlayerpass
4/4 files flagged
- ZeroLeakspass
Score: 93/100 · 2 sections analyzed
What does this agent skill do?
System Watchdog
Monitor system resources and flag wasteful or suspicious processes. Works standalone as a bash script — see openclaw.md for scheduled cron setup.
Standalone Usage
Run the check script directly — no OpenClaw required:
bash check.sh
Outputs a JSON object to stdout. Parse it however you like — pipe to jq, feed to an agent, integrate into your own monitoring stack.
Output Format
{
"suspicious": true,
"summary": {
"ram": "12.3/31.2 GB (39%)",
"swap": "0.5/8.0 GB (6%)",
"load": "1.2/0.8/0.6",
"cores": 8,
"disk": "120/256 GB (45%)"
},
"issues": [
{
"type": "high_ram",
"description": "claude (PID 1234) 4650MB RAM",
"details": { "pid": 1234, "name": "claude", "cpu_pct": 2.1, "mem_mb": 4650, "elapsed": "3d" }
}
],
"top_processes": [
{ "pid": 1234, "name": "claude", "cpu_pct": 2.1, "mem_mb": 4650, "elapsed": "3d" }
]
}
suspicious: true→ at least one issue exceeded a thresholdsuspicious: false→ system looks healthy
Thresholds
| Check | Threshold | Issue Type |
|---|---|---|
| Process RAM | > 4096 MB | high_ram |
| Process CPU | > 50% | high_cpu |
| Stale processes | Running > 2 days AND using > 100 MB or > 1% CPU | stale |
| Disk usage | > 80% on root mount | disk |
Common Offenders
claude/codex— AI coding agents left running for dayswhisper/whisper-server— speech-to-text servers consuming GPU/RAMpython/python3— runaway scripts or leaked processesnode— dev servers or builds that never stopped
Agent Workflow (for AI agents)
- Run
check.sh - Parse the JSON output
- If
suspiciousisfalse→ do nothing (no report needed) - If
suspiciousistrue→ format a concise report and notify the user
Suggested Report Format
⚠️ System Watchdog Report
📊 System: RAM 12.3/31.2 GB (39%) | Swap 0.5/8.0 GB (6%) | Load 1.2/0.8/0.6
💾 Disk: / 45% (120/256 GB)
🔴 Issues Found:
HIGH RAM — claude (PID 1234)
CPU: 2.1% | RAM: 4650 MB | Running: 3 days
→ Likely stale, safe to kill
💡 Suggested: kill 1234
Platform Notes
- macOS only —
check.shusessysctl,vm_stat, and macOSpsflags. It won't work on Linux without adaptation (replace withfree,/proc/meminfo, etc.). - Intermittent jq-style parse error — the script occasionally fails on first run due to a race in process scanning. Retry once before reporting failure.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/tychohq/agent-skills/system-watchdog">View system-watchdog on skillZs</a>