skill-cleaner

---
name: skill-cleaner
description: "Use when an agent needs to audit Codex/OpenClaw skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions from steipete/agent-scripts."
source: https://github.com/steipete/agent-scripts/tree/main/skills/skill-cleaner
generated: 2026-05-27T20:56:28.978Z
category: tool
audience: engineers
---

## When to use

- Trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove.
- Using the skill-cleaner skill's upstream workflow, guardrails, and local-tool assumptions.
- Auditing commands or operational steps before changing skill cleaner behavior.
- Needing a compact agent reference for audit Codex/OpenClaw skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.

## Key concepts

### Workflow

1. Run the analyzer from this skill directory or repo root: Useful variants: 2. Read the report in this order: Skill Budget: GPT-5.5 context size, 2% skills budget, Codex-budgeted usage, and pre-budget full-list 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 $skill mention, SKILL.md...

### Analyzer Notes

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. It reads ~/.codex/modelscache.json for GPT-5.5 contextwindow; fallback is 272,000 tokens...

### Output Policy

Suggest first; edit only when the user asks. If asked to apply cleanup, make small grouped commits: descriptions, deletes, config disables. Do not delete ignored/untracked skill dirs without naming the destination or confirming they are disposable.

## API reference

```
npx skills add steipete/agent-scripts --skill skill-cleaner
```

Install the skill-cleaner skill from steipete/agent-scripts.

```
npx skills add steipete/agent-scripts --skill skill-cleaner
```

```
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3.
```

Command or snippet documented by the upstream skill-cleaner skill.

```
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3
```

```
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs.
```

Command or snippet documented by the upstream skill-cleaner skill.

```
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 6 --max-log-mb 800 --deep-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --context-tokens 272000 --budget-percent 2 --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --root ~/Dropbox/boxd/skills --no-logs
```

## Gotchas

- Prefer deleting repo-local or agent-scripts duplicates when Codex built-ins cover them.
- Do not delete ignored/untracked skill dirs without naming the destination or confirming they are disposable.

---
Generated by SkillMake from https://github.com/steipete/agent-scripts/tree/main/skills/skill-cleaner on 2026-05-27T20:56:28.978Z.
Verify against source before relying on details.

File: ~/.claude/skills/skill-cleaner/SKILL.md