What is ccaudit CLAUDE.md?

Project instructions for ccaudit, a TypeScript command-line tool that audits unused Claude Code agents, skills, MCP servers, commands, hooks, and memory files.

Understanding the pnpm monorepo, locating the CLI and domain packages, and following the project's build, test, formatting, and validation workflow.

They give a coding agent the repository's layout, tools, terminology, and verification commands so it can work consistently.

How fabio-dee/ccaudit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fabio-dee/ccaudit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fabio-dee/ccaudit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fabio-dee/ccaudit

Made for: Claude Code.

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/instructions/fabio-dee/ccaudit/claude-md/github.svg)](https://agentmods.dev/instructions/fabio-dee/ccaudit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/fabio-dee/ccaudit/claude-md"><img src="https://agentmods.dev/badge/instructions/fabio-dee/ccaudit/claude-md/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/instructions/fabio-dee/ccaudit/claude-md"><img src="https://agentmods.dev/badge/instructions/fabio-dee/ccaudit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,892 This file is loaded in full into every session.

When invoked 1,892 The same file — it is already loaded in full.

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	$0.01892	$0.01892
Opus 5.5	$0.00757	$0.00757
Sonnet 5.5	$0.00378	$0.00378
Haiku 4.5	$0.00189	$0.00189

Measured 2mo ago against content hash 03d87843bc0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ccaudit CLAUDE.md 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 2mo 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project memory for AI coding assistants working in this repo. For end-user docs see README.md; release notes in CHANGELOG.md; JSON envelope reference in docs/JSON-SCHEMA.md.

Project

ccaudit is a CLI that audits Claude Code's ghost inventory: agents, skills, MCP servers, commands, hooks, and memory files defined once but rarely invoked. It quantifies the per-session token cost and ships one reversible command to archive ghosts. Companion tool to ccusage.

Tech stack

TypeScript / Node ≥20 / pnpm 10 monorepo. CLI built on gunshi. JSON validation via valibot.safeParse. Globbing via tinyglobby. Tables via cli-table3. Bundled via tsdown (Rolldown). Tested via vitest 4.1. Formatted via oxfmt. Linted via eslint 9 flat config. Zero runtime dependencies: everything is devDependencies and bundled into dist/.

Monorepo layout

apps/ccaudit/        CLI entry, subcommand wrappers, integration tests, dist/ bundle
packages/internal/   Domain code: scanner, remediation, framework, token, history, report
packages/terminal/   Terminal renderers (tables, panels, color)
docs/                User-facing reference docs

Commands

pnpm verify         # full gate: typecheck + lint + build + test + format:check
pnpm test           # vitest only (TZ=UTC enforced, no watch in CI)
pnpm build          # tsdown bundle into apps/ccaudit/dist/
pnpm format         # oxfmt --write .

CI is tag-triggered only. Pre-push hook runs format + lint (not tests). Run pnpm verify locally before opening a PR.

Conventions

In-source tests belong in if (import.meta.vitest) { ... } blocks at the bottom of source files. Integration tests live under apps/ccaudit/src/__tests__/. The bundler strips in-source tests via define: { 'import.meta.vitest': 'undefined' }.
Result types: prefer @praha/byethrow Result over throwing across module boundaries.
Paths: use forward slashes in glob patterns (tinyglobby normalizes). os.homedir() for home expansion. Never hard-code /Users/... or /home/....
Time: ISO 8601 UTC strings (new Date().toISOString()). Tests run with TZ=UTC.
Errors at boundaries: at the outermost layer (CLI command, history writer), catch and degrade gracefully. Inside the domain, propagate via Result.
Frontmatter writes on memory files: always go through writeFilePreservingMtime from packages/internal/src/remediation/fs-utils.ts. A bare fs.writeFile destroys the staleness signal.

Read the full file on GitHub · 92 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.

2mo ago First seen · 92 lines · 1,892 tokens per session scan A 03d87843bc0f

Subscribe to this mod's changes

ccaudit CLAUDE.md is an instructions file published in the GitHub repository fabio-dee/ccaudit (47 stars, last pushed 6mo ago), licensed MIT. It adds 1,892 tokens to every session, about $0.0076 per session on Opus 5.5. 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 2026-08-30.

Building agents

ccaudit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ccaudit CLAUDE.mdfabio-dee/ccaudit	Instructions file	47	6mo ago	MIT	A	1,892	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ccaudit: Instructions file for Claude Code