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 audit-confgit 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/audit-conf)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/audit-conf"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/audit-conf/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/audit-conf"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/audit-conf.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 | $0.00023 | $0.00935 |
| Opus 5 | $0.00012 | $0.00467 |
| Sonnet 5 | $0.00005 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
audit-conf 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit this project's Claude Code configuration against the latest global config. Fix drift, remove duplicates, regenerate caches, and optimize.
Step 1 — Project CLAUDE.md
Read .claude/CLAUDE.md or CLAUDE.md at project root.
If it exists:
- Read
~/.claude/CLAUDE.md(global config) - Compare section by section. Remove from project CLAUDE.md anything that is
identical or near-identical to the global config:
- Mindset engineering rules → in global, remove from project
- Critical-thinking / anti-complacency → in global, remove from project
- Backlog system rules → in global, remove from project
- Handoff rules → in global, remove from project
- Check for obsolete references:
/oneshot→ removed module, delete any mention[SYSTEM-HANDOFF-CRITICAL]→ removed behavior, delete any mentionWORKER_COMMAND→ renamed toWORKER_MODE, update if found- Old commit rules referencing "Co-Authored-By: Claude" → should not exist
- Check that stack-specific rules are present and accurate:
- Build/lint/test commands match actual project config files
- Framework conventions match actual code patterns
- If rules reference files that don't exist → flag
- Run
/claude-md-boostif the CLAUDE.md is thin or generic
If it doesn't exist:
- Run
/claude-md-initto generate one
Show the diff of any changes before proceeding.
Step 2 — BACKLOG
If BACKLOG/ exists:
- Run
/backlog-statusto regenerate INDEX.md from ticket files - Check for orphan tickets:
- Files without proper
# TYPE-XXX: Titleheading → flag - Duplicate IDs across PENDING and DONE → flag
- Files without proper
- Check that tickets in DONE/ have
**Statut:** Faitin their content - Report: "X pending / X done, INDEX.md regenerated"
If BACKLOG/ doesn't exist:
- Skip (not all projects need a backlog)
Step 3 — Local settings
Read .claude/settings.local.json if it exists.
Check:
- Permissions — are they appropriate for this project's stack?
- Missing common permissions for the detected stack → suggest
- Overly broad permissions (
Bash(*)) → flag
- Hooks — any obsolete hook references?
bun .../src/cli.ts(old command-guard) → should be wrapper- Any hook pointing to files that don't exist → flag
- If no local settings exist → OK (global settings apply)
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.
- 9d ago First seen · 99 lines · 23 tokens per session scan A 92f8a6172c96
audit-conf is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 935 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.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
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…
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.
review-pr
Perform a comprehensive code review of a pull request.