system-watchdogSystem resource monitoring that detects wasteful or suspicious processes. Outputs structured JSON for any consumer.
Install via ClawdBot CLI:
clawdbot install BrennerSpear/system-watchdogMonitor system resources and flag wasteful or suspicious processes. Works standalone as a bash script ā see openclaw.md for scheduled cron setup.
Run the check script directly ā no OpenClaw required:
bash check.sh
Outputs a JSON object to stdout. Parse it however you like ā pipe to jq, feed to an agent, integrate into your own monitoring stack.
{
"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 ā at least one issue exceeded a thresholdsuspicious: false ā system looks healthy| 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 |
claude / codex ā AI coding agents left running for dayswhisper / whisper-server ā speech-to-text servers consuming GPU/RAMpython / python3 ā runaway scripts or leaked processesnode ā dev servers or builds that never stoppedcheck.shsuspicious is false ā do nothing (no report needed)suspicious is true ā format a concise report and notify the userā ļø System Watchdog Report
š System: RAM 12.3/31.2 GB (39%) | Swap 0.5/8.0 GB (6%) | Load 1.2/0.8/0.6
š¾ Disk: / 45% (120/256 GB)
š“ Issues Found:
HIGH RAM ā claude (PID 1234)
CPU: 2.1% | RAM: 4650 MB | Running: 3 days
ā Likely stale, safe to kill
š” Suggested: kill 1234
check.sh uses sysctl, vm_stat, and macOS ps flags. It won't work on Linux without adaptation (replace with free, /proc/meminfo, etc.).Generated Mar 1, 2026
AI development studios running multiple AI agents like Claude or Codex for extended periods can use this skill to detect resource-hogging processes. It helps prevent system slowdowns by identifying stale agents consuming high RAM or CPU, ensuring efficient resource allocation during model training or testing.
Companies deploying speech-to-text services using Whisper servers can monitor for wasteful processes that consume excessive GPU or RAM. This skill flags issues like stale servers, enabling proactive maintenance to avoid service disruptions and optimize hardware usage in call centers or transcription services.
DevOps teams managing macOS-based servers can integrate this skill into their monitoring stack to detect high disk usage or runaway scripts. It provides structured JSON output for automated alerts, helping maintain system stability and prevent outages in web hosting or cloud infrastructure environments.
Research labs running long-term computational experiments on macOS systems can use this skill to identify processes exceeding thresholds, such as Python scripts leaking memory. This ensures efficient use of limited resources, reducing costs and improving experiment reliability in academic or pharmaceutical research.
Freelancers or small businesses using macOS for development work can deploy this skill to catch issues like Node.js dev servers left running. It offers a simple bash script for standalone checks, helping non-technical users maintain system performance without complex setup, ideal for web development or content creation.
Offer this skill as part of a SaaS platform that provides automated system monitoring and alerts. Customers pay a monthly fee for access to enhanced features like historical data, custom thresholds, and integrations with popular tools, generating recurring revenue from tech teams and IT departments.
Provide consulting services to help businesses integrate this skill into their existing monitoring stacks, such as setting up cron jobs or adapting it for Linux. Revenue comes from one-time project fees or ongoing support contracts, targeting enterprises needing customized solutions.
Distribute the basic skill for free as open-source to build a user base, then monetize through premium add-ons like advanced analytics, multi-platform support, or priority support. This model attracts individual developers and upsells to larger teams seeking enhanced functionality.
š¬ Integration Tip
For easy integration, pipe the JSON output to tools like jq for parsing or feed it directly into monitoring dashboards; set up a cron job using the provided openclaw.md guide for automated checks.
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
Essential Docker commands and workflows for container management, image operations, and debugging.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.