Agent skill · operations · steipete
skill-cleaner
Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.
Why this skill is useful
Adds executable scripts for skill auditing and management that streamline the process of maintaining skill inventories.
What it needs
Requires node installed locally. About 2k tokens when loaded. Last updated 2026-08-06. 6,510 stars on the source repository.
What this skill does
Skill Cleaner Use this when trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove. Workflow 1. Run the analyzer from this skill directory or repo root: Useful variants: 2. Read the report in this order: Skill Budget: live Codex inventory, 2% budget, budgeted usage, and full-description pressure. Description candidates: long descriptions where relaxed grammar saves prompt budget. Duplicates: same skill name or near-identical description/body across Codex, plugin cache, repo siblings, and personal skill roots. Unused candidates: no recent user mention or actual SKILL.md read in recent Codex/OpenClaw logs. Root summary: where skills came from and whether config marks them disabled. 3. Before deleting or editing: Verify the kept copy exists and is loaded. Prefer deleting repo-local or agent-scripts duplicates when Codex built-ins cover them. Keep repo-local OpenClaw maintainer skills when they encode repo policy or live operations. Preserve trigger nouns in descriptions: product, tool, action, object. Analyzer Notes By default, codex debug prompt-input supplies the exact model-visible skill list, order, names, and aliased paths. --no-live forces the broader filesystem fallback. The broad filesystem scan remains for duplicate, disabled, and archived-cache diagnostics; it is not treated as the loaded inventory. The script mirrors Codex's model-visible line shape: - name: description (file: path). It applies Codex-like frontmatter rules: YAML frontmatter only, default name from parent dir, single-line sanitized name and description. It follows Codex core-skills/src/render.rs: 2% of raw contextwindow, token cost ceil(utf8bytes / 4), then full descriptions -> equal description truncation -> omitted minimum lines. Alias-table line cost is included. It reads ~/.codex/modelscache.json for GPT-5.5 contextwindow; fallback is 272,000 tokens and 2%. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills steipete/skill-cleaner