An audit for Claude Code setup files, including CLAUDE.md instructions and rule files. It checks their size, organization, duplicates, origin, and possible candidates for clearer enforcement.

Use it before a major setup refactor, after adding many rules, or when coding sessions feel slow or unfocused.

It shows when setup instructions have become too long, repetitive, inconsistent, or hard to maintain. It can also point out missing or underused configuration areas.

bp-audit — Skill for Claude Code by kulmam92

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 kulmam92/cc-best-practices-marketplace --skill bp-audit

Clone the repo

git clone --depth 1 https://github.com/kulmam92/cc-best-practices-marketplace

Made for: Claude Code.

Or install cc-best-practices, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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/kulmam92/cc-best-practices-marketplace/bp-audit/github.svg)](https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-audit)

Your own site

<a href="https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-audit"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kulmam92/cc-best-practices-marketplace/bp-audit"><img src="https://agentmods.dev/badge/skills/kulmam92/cc-best-practices-marketplace/bp-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 887 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00887
Opus 5	$0.00028	$0.00443
Sonnet 5	$0.00011	$0.00177
Haiku 4.5	$0.00006	$0.00089

Measured 11d ago against content hash a6b865dd9e51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bp-audit 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 11d 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.

plugins/cc-best-practices/skills/bp-audit/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Health Audit

A "linter for your linter config." Checks whether your Claude Code setup is lean, consistent, and making the most of the three enforcement tiers (advisory -> prompting -> deterministic).

Steps

CLAUDE.md budget check -- Read the project's root CLAUDE.md. Count lines (excluding blank lines and comments). Report:
- Current line count vs 150-line ceiling (~2.5k token budget)
- If over 120 lines: warn and suggest moving domain-specific rules to .claude/rules/
- If under 50 lines: note that the setup may be underutilized -- suggest running /bp-setup if sections are empty
- Check for subdirectory CLAUDE.md files and report their line counts too
Rule inventory -- Scan .claude/rules/ directory. For each rule file, report:
- Filename
- Scope: project-wide (no paths frontmatter) or path-scoped (list the paths)
- Provenance: was it deployed by /bp-setup (check for standard names: verification.md, refactoring.md, session-discipline.md, anti-patterns.md) or added via /bp-learn (check for provenance comment)?
- Migrated framework content: if a rules file is large (>100 lines) and doesn't match bp-setup standard names or bp-learn provenance, flag it as "migrated framework content" and note its approximate token cost (~17 tokens/line)
- Count total rule files. If 10+: warn about context overhead
Duplicate detection -- Search for semantically similar rules across ALL locations:
- Root CLAUDE.md
- Subdirectory CLAUDE.md files
- .claude/rules/ files
- Flag any rule that appears in multiple locations
- Recommend keeping the most targeted version (path-scoped > project-wide > CLAUDE.md)
Hook inventory -- Read .claude/settings.json and .claude/settings.local.json. Report:
- Which hooks are configured (Stop, PreToolUse, PostToolUse)
- Suggest the equivalent profile name:
  - No hooks = minimal
  - Stop hook only = standard
  - Stop + PreToolUse + PostToolUse = strict
- If no hooks: suggest considering at least standard profile (run /bp-setup to add)

Read the full file on GitHub · 61 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.

11d ago First seen · 61 lines · 56 tokens per session scan A a6b865dd9e51

Subscribe to this mod's changes

bp-audit is a skill published in the GitHub repository kulmam92/cc-best-practices-marketplace (2 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 887 once invoked, about $0.0003 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.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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