system-watchdog
System resource monitoring that detects wasteful or suspicious processes. Outputs structured JSON for any consumer.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- system-watchdog
- description
- System resource monitoring that detects wasteful or suspicious processes. Outputs structured JSON for any consumer.
03 SKILL.md 正文
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.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.