ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified system Safety 4/5

clawdscan

Diagnose Clawdbot/OpenClaw health — session bloat, zombies, stale files, AND skill dependency validation. Zero dependencies, single Python file.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cheenu1092-oss/clawdscan
Or

What This Skill Does

ClawdScan is a robust, zero-dependency diagnostic tool designed specifically for the OpenClaw and Clawdbot ecosystem. It functions as an internal system monitor, parsing session JSONL files to provide deep insights into the operational health of your agent infrastructure. The tool excels at identifying 'bloat'—sessions that have grown excessively large due to long conversation histories or runaway tool loops—and detecting 'zombie' sessions, which are orphaned files that consume storage without providing any utility. By providing granular visibility into tool usage and model switching patterns, ClawdScan allows administrators to optimize performance, manage disk storage, and ensure that agent interactions remain efficient and cost-effective.

Installation

For standard Clawdbot environments, execute clawdbot skill install clawdscan in your terminal. For those requiring a lightweight standalone version, the tool is distributed as a single Python file. Simply clone the source from openclaw/skills/skills/cheenu1092-oss/clawdscan, ensure the file is executable via chmod +x clawdscan.py, and run it directly. No additional libraries or virtual environments are required, making it ideal for integration into restricted server environments.

Use Cases

ClawdScan is indispensable for infrastructure maintenance. Use it to audit storage usage across large-scale deployments, identify which agents are most resource-intensive, and verify if specific tools are causing session bloating. It is frequently utilized in cron jobs for automated maintenance, such as archiving sessions inactive for over 30 days or purging zero-length zombie files. Additionally, developers can use the inspect and tools modules to debug agent behavior, observing how specific LLMs handle complex tool chains within a session.

Example Prompts

  1. "ClawdScan, please perform a full health check on all agents and list the top 5 sessions consuming the most disk space."
  2. "Identify all zombie sessions created in the last 48 hours and provide a summary report on their disk impact."
  3. "Analyze the tool usage frequency for my 'research-agent' and suggest any cleanup actions to reduce session bloat."

Tips & Limitations

Always perform a backup of your session directory before running mass deletion commands with the --execute flag. While ClawdScan is highly accurate at identifying staleness, confirm that your retention policies align with your business requirements before enabling automated cleanup. The tool reads local files directly, so ensure the system user running ClawdScan has sufficient read permissions on your storage volume. For very large deployments (10,000+ sessions), consider running the scan command during off-peak hours to minimize disk I/O impact.

Metadata

Stars3875
Views1
Updated2026-04-07
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cheenu1092-oss-clawdscan": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#maintenance#diagnostic#storage#optimization#monitoring
Safety Score: 4/5

Flags: file-read, file-write