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 auditgit 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)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/audit"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/audit.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 5.1 | $0.00017 | $0.03145 |
| Opus 5 | $0.00009 | $0.01572 |
| Sonnet 5 | $0.00003 | $0.00629 |
| Haiku 4.5 | $0.00002 | $0.00314 |
Grade A, and why
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 6d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a structured code audit on this project. Adapts to the detected stack.
Modes:
/audit— full audit, all relevant axes, all files/audit security(or tests, architecture, etc.) — full audit, single axis/audit --changed— incremental: only files changed since the last audit report/audit --since abc123— incremental: only files changed since the given commit or date/audit --changed security— incremental + single axis/audit --dry-run— full audit, report only, no tickets created/audit --dry-run security— single axis, no tickets
Step 1 — Context & scope
-
Read
CLAUDE.md(project root or.claude/). If none exists:- Tell the user: "No CLAUDE.md found. Run
/audit-conffirst to generate one, then re-run/audit." - Stop.
- Tell the user: "No CLAUDE.md found. Run
-
From CLAUDE.md, extract:
- Stack (languages, frameworks, DB, infra)
- Build/test commands
- Project conventions
-
Check for previous audit reports:
ls -t audit-reports/*.md 2>/dev/null | head -1- If found → note the filename and its date, used for delta comparison in Step 7
-
Parse arguments and determine mode:
Incremental mode (if
--changedor--sincein arguments):--changed: find the date of the last audit report. If none exists, tell the user "No previous audit found — running full audit instead." and fall back to full mode. Get changed files:git diff --name-only --diff-filter=ACMR $(git log --since="YYYY-MM-DD" --format=%H | tail -1)..HEAD(using the last report date)--since <ref>: get changed files:git diff --name-only --diff-filter=ACMR <ref>..HEAD- Store the list of changed files. These will be the ONLY files explored and reviewed.
- If 0 changed files → tell user "No files changed since [ref]. Nothing to audit." and stop.
- Remaining arguments after
--changed/--since <ref>are treated as axis filter.
Full mode (default):
- If
$ARGUMENTSis provided (and not--changed/--since) → audit ONLY that axis - If no argument → auto-detect relevant axes (see Step 2)
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.
- 6d ago First seen · 312 lines · 17 tokens per session scan A 19ba38b60445
audit is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 3,145 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.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
ralphctl-code-review-and-quality
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…