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 agentmods add commands/fabio-dee/ccaudit/ccaudit-bustgit clone --depth 1 https://github.com/fabio-dee/ccauditWrote 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/commands/fabio-dee/ccaudit/ccaudit-bust)<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>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 | $0.00000 | $0.04198 |
| Opus 5 | $0.00000 | $0.02099 |
| Sonnet 5 | $0.00000 | $0.00840 |
| Haiku 4.5 | $0.00000 | $0.00420 |
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.
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-ghostsfrom 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.
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.
- 5d ago First seen · 345 lines · 0 tokens per session scan A 251a7cbc4500
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.