claude-md-cleanup

claude-md-cleanup is a skill for Claude Code, Codex from Bidiche49/claude-conf. It costs 19 tokens per session (485 once invoked), scanned A, original, MIT.

A cleanup guide for a project's CLAUDE.md file, which contains instructions for coding-agent sessions.

In plain words
What is it for?
Use it to compare project instructions with global settings, then classify content as removable, retainable, or needing reformulation.
Why use it?
It removes general rules already supplied elsewhere and keeps instructions that are specific to the project, making the file shorter and clearer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to compare project instructions with global settings, then classify content as removable, retainable, or needing reformulation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bidiche49/claude-conf/claude-md-cleanup
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 Bidiche49/claude-conf --skill claude-md-cleanup
Clone the repo
git clone --depth 1 https://github.com/Bidiche49/claude-conf

Made for: Claude Code, Codex.

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.

agentmods badge for claude-md-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-cleanup/github.svg)](https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-cleanup)
Your own site
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-cleanup"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-cleanup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-md-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-cleanup"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/claude-md-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00485
Opus 5 $0.00010 $0.00243
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00049

Measured 12d ago against content hash e690a87aaf03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claude-md-cleanup scanned grade A with 0 findings 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 12d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-md-kit/skills/claude-md-cleanup/SKILL.md · 45 lines

What it actually says

Analyze the project CLAUDE.md and remove everything already covered by the global config or installed modules. Keep only what's specific to this project.

Process

  1. Read the project's CLAUDE.md

  2. Read ~/.claude/CLAUDE.md and identify installed modules by scanning for markers:

    • <!-- critical-thinking:start --> — mindset, anti-complaisance, debugging approach covered
    • <!-- backlog:start --> — ticketing system covered
    • Also check for: handoff system, supervisor rules, general rules (no AI mention, documentation, etc.)
  3. Classify each section of the project CLAUDE.md:

    • SUPPRIMER — duplicate of global (same concept, even if different wording). Examples:
      • Ticketing/backlog rules → covered by backlog-kit
      • Handoff/context saving → covered by handoff-kit
      • "No band-aid fixes" / "understand before coding" → covered by critical-thinking
      • "Never mention Claude/AI" → covered by global general rules
      • Generic dev advice ("write tests", "be clean") → useless, remove
    • GARDER — specific to this project (stack conventions, build commands, architecture, project-specific rules)
    • REFORMULER — mix of generic + specific → keep only the specific part
  4. Present the plan to the user:

    SECTIONS A SUPPRIMER (doublons avec global) :
    - "[section name]" — reason (covered by [module/section])
    
    SECTIONS A GARDER :
    - "[section name]" — reason
    
    SECTIONS A REFORMULER :
    - "[section name]" — keep [specific part], remove [generic part]
    
  5. Wait for explicit validation before writing.

  6. Write the cleaned CLAUDE.md. Preserve the structure and intent of kept sections.

Key rule

Detect by MEANING, not string matching. "Pas de fix en pansement" and "No band-aid fixes" are the same concept — both must be flagged as duplicates.

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.

  1. 12d ago First seen · 45 lines · 19 tokens per session scan A e690a87aaf03

Subscribe to this mod's changes

claude-md-cleanup is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 485 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-plugins · 41 tokens

issue-triage

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

FlorianBruniaux/claude-code-plugins · 81 tokens

atomic-wiki

Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…

damusix/atomic-claude · 204 tokens

check-cache-bugs

Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.

FlorianBruniaux/claude-code-plugins · 38 tokens

atomic-review

Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.

damusix/atomic-claude · 63 tokens

git-ai-archaeology

Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.

FlorianBruniaux/claude-code-plugins · 47 tokens