audit-router

Shared guidance for two audits that check metadata in coding add-ons against defined rules. Metadata is the structured information, such as names and options, stored at the top of command and skill files.

In plain words
What is it for?
Use it when auditing command, skill, or agent files, choosing terminal, JSON, or Markdown output, or applying safe mechanical fixes.
Why use it?
It keeps command and skill checks consistent, making it easier to find invalid fields, warnings, and other maintenance issues.

Skill for Claude CodeCodex

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 skills/data-wise/craft/audit-router
Any agent
npx skills add Data-Wise/craft --skill audit-router
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft

Made for: Claude Code, Codex.

Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 747 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 $0.00180 $0.00747
Opus 5 $0.00090 $0.00374
Sonnet 5 $0.00036 $0.00149
Haiku 4.5 $0.00018 $0.00075

Measured 2d ago against content hash 8a4b0786cbfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-router 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 2d 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.

skills/code/audit-router/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Router — Shared Vocabulary for craft's Schema-Audit Commands

Two commands audit craft's own frontmatter against a schema and share one vocabulary:

Command Validates Against
/craft:code:command-audit commands/, skills/, agents/ frontmatter _schema.json
/craft:code:skill-standards skills/**/SKILL.md vendored Anthropic authoring standards (docs/reference/SKILL-STANDARDS.md)

Both commands stay independently slash-invocable — this skill holds the shared vocabulary and each command's full reference body, not a replacement entry point.

Shared Flag Vocabulary

Both commands accept the same two flags with the same meaning:

  • --format terminal|json|markdown — output rendering only, default terminal. Never changes what is checked.
  • --fix — auto-fixes safe mechanical issues only, never prose or descriptions:
    • command-audit --fix: removes invalid frontmatter fields, renames argsarguments.
    • skill-standards --fix: strips rot-prone version tags from reference headers, normalizes frontmatter key casing/order, inserts TOC stubs in oversized reference files.

Both share the same health-score formula (100 − errors×5 − warnings×2, floored at 0) and the same exit-code convention (0 clean, 1 warnings-only, 2 errors — command-audit --strict also treats warnings as errors, matching skill-standards' own error-severity checks).

skill-standards carries one extra flag (--refresh-standards) with no command-audit equivalent — documented in its own reference only, not promoted to the shared set.

Full Reference Bodies

Not This Skill

deps-audit, deps-check, docs-check are not schema-audit-shaped — they're generic cross-project tools (dependency security/freshness for any project, or a full docs/site preflight+deploy pipeline) with incompatible flag surfaces. They stay independent commands with their own bodies, not references under this skill.

Read the full file on GitHub · 49 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 49 lines · 180 tokens per session scan A 8a4b0786cbfd

Subscribe to this mod's changes

audit-router is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed 17d ago), licensed MIT. It adds 180 tokens to every session and 747 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

architecture-review

Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do…

codenamev/ai-software-architect · 80 tokens

architecture-status

Reports on the health and state of architecture documentation (counts of ADRs, reviews, activity levels, documentation gaps). Use when the user asks "What's our architecture status?", "Show architecture documentation", "How many ADRs do we have?", "What decisions are documented?", "Architecture health check", or wants…

codenamev/ai-software-architect · 104 tokens

pragmatic-guard

Enables and configures Pragmatic Guard Mode (YAGNI Enforcement) to prevent over-engineering. Use when the user requests "Enable pragmatic mode", "Turn on YAGNI enforcement", "Activate simplicity guard", "Challenge complexity", or similar phrases.

codenamev/ai-software-architect · 58 tokens

specialist-review

Conducts a focused review from ONE specific specialist's perspective (e.g., Security Specialist, Performance Expert). Use when the user requests "Ask [specialist role] to review [target]", "Get [specialist]'s opinion on [topic]", "Have [role] review [code/component]", or when they want deep expertise in ONE specific…

codenamev/ai-software-architect · 101 tokens

create-adr

Creates a NEW Architectural Decision Record (ADR) documenting a specific architectural decision. Use when the user requests "Create ADR for [topic]", "Document decision about [topic]", "Write ADR for [choice]", or when documenting technology choices, patterns, or architectural approaches. Do NOT use for reviews (use…

codenamev/ai-software-architect · 83 tokens

list-members

Displays the roster of architecture team members with their specialties and expertise areas. Use when the user asks "Who's on the architecture team?", "List architecture members", "Show me the architects", "What specialists are available?", "Who can I ask for reviews?", or wants to discover available experts. Do NOT…

codenamev/ai-software-architect · 84 tokens