skill-cleaner
Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.
Skill by az9713
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/az9713-skill-cleaner
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, finance, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
skill-cleaner- Description
- Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.
- License
- MIT
- Instructions
- 58 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- openai.yaml · agents/
- skill-cleaner.test.ts · scripts/
- skill-cleaner.ts · scripts/
SKILL.md (first lines)
# 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: ```bash node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3 ``` Useful variants: ```bash node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-live --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 node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --root ~/.agents/skills --root-only --no-logs ``` 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 `context_window`, token cost `ceil(utf8_bytes / 4)`, then full descriptions -> equal description truncation -> omitted minimum lines. Alias-table line cost is included. - It reads `~/.codex/models_cache.json` for GPT-5.5 `context_window`; fallback is 272,000 tokens and 2%. - It scans only normal Codex/plugin/repo skill roots by default. Extra folders such as Dropbox archives are included only with `--root <path>`. - `--root-only` requires at least one `--root <path>`, skips the live Codex inventory, and scans only those supplied roots. - It realpath-dedupes roots, so symlinked/junction roots do not create false duplicates. - For duplicate names, it reports description/body similarity and suggests deletion candidates only when bodies are near copies. Keep priority defaults to direct Codex system skills, then direct Codex skills, then plugin skills, then personal/repo copies. - It scans `~/.codex/history.jsonl` and recent `~/.codex/sessions/**/*.jsonl` by default. Add `--deep-logs` for archived sessions and common OpenClaw/Clawd log folders. - Usage evidence is heuristic: user `$skill`/`use skill` mentions and paths observed in tool-call arguments. ## 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.
From az9713/agent-scripts-windows, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/az9713/agent-scripts-windows
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from az9713
- 0.461score
codex-first
az9713
Claude Code-only work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while Claude specifies…
SkillBFreshness: BClaude Code +9 - 0.430score
offer-shaper
az9713
Convert a vague AI idea or buyer pain into a concrete paid offer with buyer, promise, deliverable, price, proof mechanism, and sales path.
SkillCFreshness: C★ 1Claude Code +9 - 0.430score
context-reset
az9713
Preserve durable project state before clearing or compacting context so Claude Code can reset without losing business, technical, and verification state.
SkillCFreshness: C★ 1Claude Code +9 - 0.430score
break-test
az9713
Red-team a project, automation, app, or offer by trying to break it technically, commercially, operationally, and in front of a buyer.
SkillCFreshness: C★ 1Claude Code +9 - 0.430score
council-session
az9713
Run the full Idea-to-Capital council loop across buyer, CFO, technical, distribution, verification, and packaging perspectives.
SkillCFreshness: C★ 1Claude Code +9 - 0.430score
opportunity-triage
az9713
Evaluate an AI project, automation, SaaS, content product, or service idea for buyer demand, profitability, speed to validation, and whether to build…
SkillCFreshness: C★ 1Claude Code +9
Cite this page
skill-cleaner. Agent Mart. https://agentmart.dev/skills/az9713-skill-cleaner (last updated 2026-10-24)