What is claude-cleanup?

A cleanup tool for Claude Code settings, including skills, hooks, plugins, commands, and stored configuration. Claude Code is a coding assistant that can be extended with these project and user settings.

Use it to audit the setup, preview problems with a dry run, or clean up one of its six audit areas.

It finds broken references, duplicate skills, outdated paths, and stale configuration that can make the assistant behave incorrectly.

claude-cleanup — Skill for Claude Code by lancewillett

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add lancewillett/ai-plugins --skill claude-cleanup

Clone the repo

git clone --depth 1 https://github.com/lancewillett/ai-plugins

Made for: Claude Code.

Or install claude-cleanup, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lancewillett/ai-plugins/claude-cleanup.svg)](https://agentmods.dev/skills/lancewillett/ai-plugins/claude-cleanup)

Your own site

<a href="https://agentmods.dev/skills/lancewillett/ai-plugins/claude-cleanup"><img src="https://agentmods.dev/badge/skills/lancewillett/ai-plugins/claude-cleanup.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,913 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.01913
Opus 5	$0.00016	$0.00957
Sonnet 5	$0.00007	$0.00383
Haiku 4.5	$0.00003	$0.00191

Measured 8d ago against content hash f339b08eef8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-cleanup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `~/.claude/settings.json`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/claude-cleanup/skills/claude-cleanup/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Configuration Cleanup

Comprehensive audit and cleanup of Claude Code configuration. Run periodically (monthly recommended) to keep your setup clean and consistent.

Arguments

No argument: Run full 6-step audit with interactive fixes
--dry-run: Report issues without making changes
--step=N: Run only step N (1-6)

Workflow

Step 1: Skill Audit

Goal: Find broken references, outdated paths, and duplicates in custom skills.

Locations to scan:

~/.claude/skills/ (global)
~/Source/.claude/skills/ (Source-level)
Project-level .claude/skills/ directories

Checks:

Broken skill references: Grep for /skill-name patterns and verify referenced skills exist
Broken command references: Grep for /command-name patterns and verify commands exist
Outdated paths: Search for old folder names that have been renamed
Duplicate skills: Compare skill names across locations

Report format:

Step 1: Skill Audit
───────────────────
Locations scanned: 3
Skills found: 12

Issues:
  ~/.claude/skills/example/SKILL.md
    ⚠ References /missing-skill (line 45) - skill not found
    ⚠ Path "old-folder/" should be "new-folder/"

Actions:
  1. Remove reference to /missing-skill or create it
  2. Update path from old-folder/ to new-folder/

If not --dry-run: Offer to fix each issue interactively.

Step 2: Hooks & Settings Audit

Goal: Verify hooks work and clean up stale permissions.

Files to check:

~/.claude/settings.json
~/.claude/settings.local.json
~/.claude/hooks/ directory

Checks:

Hook scripts exist: Verify each script referenced in settings.json exists
Orphaned scripts: Find scripts in hooks/ not referenced in settings
Redundant permissions: Flag bash commands that have dedicated tools:
- Bash(cat:*) → use Read tool
- Bash(find:*) → use Glob tool
- Bash(grep:*) → use Grep tool
One-off permissions: Flag overly specific permissions (debugging artifacts)

Read the full file on GitHub · 272 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 272 lines · 33 tokens per session scan A f339b08eef8a

Subscribe to this mod's changes

claude-cleanup is a skill published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 1,913 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

claude-cleanup