ccaudit-bust

ccaudit-bust is a command for Claude Code from fabio-dee/ccaudit. It costs 0 tokens per session (4,198 once invoked), scanned A, original, MIT.

A command for finding and selectively archiving unused Claude Code agents and skills. These are instruction files that extend or guide Claude Code.

In plain words
What is it for?
Use it to audit unused agents or skills and archive the specific ones you name, such as old marketing, Python, or GSD-related extensions.
Why use it?
It helps reduce clutter from old extensions while leaving MCP server and memory configuration files untouched.

Command for Claude Code

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.

agentmods
npx agentmods add commands/fabio-dee/ccaudit/ccaudit-bust
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.

agentmods badge for ccaudit-bust

README.md
[![agentmods](https://agentmods.dev/badge/commands/fabio-dee/ccaudit/ccaudit-bust.svg)](https://agentmods.dev/commands/fabio-dee/ccaudit/ccaudit-bust)
Your own site
<a href="https://agentmods.dev/commands/fabio-dee/ccaudit/ccaudit-bust"><img src="https://agentmods.dev/badge/commands/fabio-dee/ccaudit/ccaudit-bust.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04198
Opus 5 $0.00000 $0.02099
Sonnet 5 $0.00000 $0.00840
Haiku 4.5 $0.00000 $0.00420

Measured 5d ago against content hash 251a7cbc4500, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccaudit-bust 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 5d 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.

apps/ccaudit/.claude/commands/ccaudit-bust.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ccaudit-bust — Selective Ghost Archive

Audit the current Claude Code ghost inventory and — on your plain-English request — selectively archive the agents and skills you name. This skill uses your judgment, not rigid urgency bands, to decide what to archive.

When to use this skill: when the user says something like:

  • "clean up my marketing skills"
  • "archive any agent I haven't used in 90 days"
  • "remove all GSD-related ghost skills"
  • "find unused Python agents and delete them"
  • "what ghost skills do I have about SEO?"

Scope

This skill handles agents (~/.claude/agents/*.md) and skills (~/.claude/skills/**). These are standalone files that can be moved safely while Claude Code is running.

This skill does not touch MCP servers (entries in ~/.claude.json / .mcp.json) or memory files (CLAUDE.md frontmatter). Those require editing files that Claude Code has open, which is unsafe from inside a running session. For those, tell the user:

"For MCP servers and stale memory files, close Claude Code and run npx ccaudit-cli@latest ghost --dangerously-bust-ghosts from a standalone terminal."


Step 1 — Audit

1a. Save the scan to a temp file

ccaudit ghost --json can produce a payload larger than the Bash tool's output buffer (typically 100+ items for a well-used Claude Code setup). Always redirect to a file first, then read from the file — don't parse stdout directly.

Choose the window before running. ghost --json defaults to a 7-day unused-since window, so items unused for longer than 7 days are already in the candidate set — but the daysSinceLastUse field will not reach back further than the scan window. If the user specifies an age window (e.g. "unused for 90 days", "90 days+", "3 months+", "anything old", "stale for a quarter"), derive --since <WINDOW> before running ghost so age-based filtering later in Step 2 is sound. If the request is non-age-based (e.g. "archive marketing-copy", "clean up SEO skills"), keep the default.

Read the full file on GitHub · 345 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.

  1. 5d ago First seen · 345 lines · 0 tokens per session scan A 251a7cbc4500

Subscribe to this mod's changes

ccaudit-bust is a command published in the GitHub repository fabio-dee/ccaudit (47 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,198 tokens. 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.