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.
npx skills add Bidiche49/claude-conf --skill claude-md-cleanupgit clone --depth 1 https://github.com/Bidiche49/claude-confWrote 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.
[](https://agentmods.dev/skills/bidiche49/claude-conf/claude-md-cleanup)<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.
<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>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 | $0.00019 | $0.00485 |
| Opus 5 | $0.00010 | $0.00243 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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.
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
-
Read the project's
CLAUDE.md -
Read
~/.claude/CLAUDE.mdand 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.)
-
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
- SUPPRIMER — duplicate of global (same concept, even if different wording). Examples:
-
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] -
Wait for explicit validation before writing.
-
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.
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.
- 12d ago First seen · 45 lines · 19 tokens per session scan A e690a87aaf03
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.
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.
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.
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…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
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.
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.