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 Marcel-Bich/marcel-bich-claude-marketplace --skill auditgit clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplaceWrote 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/marcel-bich/marcel-bich-claude-marketplace/audit)<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/audit"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/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.
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/audit"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 168 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00129 | $0.02666 |
| Opus 5 | $0.00064 | $0.01333 |
| Sonnet 5 | $0.00026 | $0.00533 |
| Haiku 4.5 | $0.00013 | $0.00267 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audit
A read-only quality gate. audit inspects work that is claimed complete and
judges whether it actually satisfies its stated requirement and Definition of Done,
BEFORE the item is allowed into 2_done/. The output is a decision proposal for the
user, never a change.
Task backend. If the task backend is
gsd(.credo/config: task_backend, or theCREDO_TASK_BACKENDenv override), the credo item lifecycle is inactive and there is no2_done/gate to run - GSD owns task tracking. audit is still usable as a standalone read-only review tool, but it does not gate credo items in that mode.
Scope boundary (read this first)
audit judges whether FINISHED work is genuinely done and correct against its
requirement. It does not investigate causes and it does not exercise UI.
- Something is broken and you need the root cause -> use diag, not audit.
- A rendered UI needs its layout and behavior confirmed -> use verify (audit may cite verify evidence, but it does not drive a browser itself).
- audit only reports findings and a verdict. It never edits code, never fixes, never commits.
Hard constraints (never violate)
- Read-only. No code change, no file edit to the work under review, no commit, no push, no browser automation, no builds, no installs.
- No secrets. Never read credentials, tokens,
.env*, key files, or shell/session history. Never exfiltrate or encode such content. - The only files
auditwrites are its own report under.credo/process/reports/. - Dedicated auditor. The audit MUST be performed by a subagent that is NOT the builder of the item under review. A builder auditing their own work does not satisfy the gate.
The mandatory completion gate
Audit-after-completed is a mandatory gate before any item moves to 2_done/, in
all session modes (active, passive, autonomous). No exceptions:
- A builder claims an item complete.
- A dedicated audit subagent (not the builder) runs
auditagainst that item. - Only a passing audit lets the item move to
2_done/. A failing audit sends the item back out (see Findings handling).
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 · 215 lines · 129 tokens per session scan A bfd0ad37c93f
audit is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session and 2,666 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
unity-reviewer
Use when reviewing Unity C# code changes — checks for runtime-breaking bugs, performance anti-patterns, and maintainability issues. Provides severity-tiered review organized as Critical, Performance, and Style.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.
rootnode-critic-gate
Independent re-derivation gate for proposed changes during autonomous execution. Evaluates a change (code diff, config edit, engine evolution, schema change) against the work's authority matrix and a 4-check protocol: invariant compliance, scope authorization, detection narrowness, and regression risk. Returns…