Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Add trim ladder, /context json verification metrics, rollback-first guidance, and new-session caveat.
What This Skill Does
Audits prompt context to identify what is consuming the most space, then produces a ranked list of offenders and a reversible fix plan. No changes are applied automatically. Designed for situations where slow replies, rising costs, or noisy transcripts suggest context has grown too large.
Gives a prioritized, rollback-ready fix plan based on measured context metrics rather than guesswork.
When to use it
- Diagnosing slow AI replies caused by context bloat
- Finding oversized tool output clogging session transcripts
- Identifying cron automation noise accumulating across sessions
- Spotting bloated bootstrap files like AGENTS.md or SKILL.md
- Getting a safe trim plan before modifying any config files
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: /context-clean-up
- 1Determine workspace directory and OpenClaw state directory
- 2Run the audit script to collect context size metrics across sessions
- 3Rank offenders by category: tool output dumps, automation noise, bootstrap bloat, ambient skill surface
- 4Generate a phased fix plan with expected impact and rollback steps for each change
Audit report listing top context offenders, lowest-risk fixes ordered by phase, and verification steps to confirm improvement after changes