audit-artifact

audit-artifact is a skill for Claude Code from Enovatr-Labs/SpecRoute. It costs 87 tokens per session (513 once invoked), scanned A, original, Apache-2.0.

A guided review process for checking whether a project document or agent file is complete and ready for its intended use. It supports artifacts such as product requirements, specifications, skills, commands, hooks, prompts, and rules.

In plain words
What is it for?
Use it to review an artifact against the right checklist and readiness level, such as draft, review-ready, or implementation-ready.
Why use it?
It helps find missing requirements, unclear placeholders, invalid formats, and sensitive information before the artifact is used or shared.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review an artifact against the right checklist and readiness level, such as draft, review-ready, or implementation-ready.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/enovatr-labs/specroute/audit-artifact
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.

Any agent
npx skills add Enovatr-Labs/SpecRoute --skill audit-artifact
Clone the repo
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

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 audit-artifact

README.md
[![agentmods](https://agentmods.dev/badge/skills/enovatr-labs/specroute/audit-artifact/github.svg)](https://agentmods.dev/skills/enovatr-labs/specroute/audit-artifact)
Your own site
<a href="https://agentmods.dev/skills/enovatr-labs/specroute/audit-artifact"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/audit-artifact/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.

agentmods 80×15 button for audit-artifact

Your own site · 80×15
<a href="https://agentmods.dev/skills/enovatr-labs/specroute/audit-artifact"><img src="https://agentmods.dev/badge/skills/enovatr-labs/specroute/audit-artifact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00087 $0.00513
Opus 5 $0.00044 $0.00257
Sonnet 5 $0.00017 $0.00103
Haiku 4.5 $0.00009 $0.00051

Measured 11d ago against content hash 9de34787128a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-artifact 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.

runtimes/.claude/skills/audit-artifact/SKILL.md · 58 lines

What it actually says

Audit Artifact

Use this skill when a user wants a guided readiness review of one SpecRoute artifact or a small related set of artifacts.

Inputs

Ask for any missing input before reviewing:

  1. Path - file or directory to audit.
  2. Artifact type - one of prd, spec, agent, skill, command, hook, prompt, rule, runtime, or unknown.
  3. Readiness target - draft, review-ready, or implementation-ready.

If the artifact type is omitted, infer it from the path and confirm the inference in the audit summary.

Workflow

  1. Read the artifact and its nearest README or template reference.
  2. Identify the applicable contract:
    • PRDs need goals, non-goals, metrics, rollout, risks, dependencies, and acceptance criteria.
    • Specs need stable requirement IDs, design coverage, task back-references, and validation steps.
    • Agents and skills need valid frontmatter and clear boundaries.
    • Commands, hooks, rules, and runtime layouts need vendor-native shape.
  3. Check for unresolved placeholders that are inappropriate for the readiness target.
  4. Check sanitization risk: private names, credentials, internal endpoints, customer data, or proprietary domain logic.
  5. Report findings in severity order with file references and concrete recommended fixes.

Output Shape

## Findings

- High: <blocking issue with path>
- Medium: <important non-blocking issue>
- Low: <cleanup>

## Ready?

<yes/no> for <readiness target>, with one sentence explaining why.

## Recommended Changes

- <smallest concrete edit>

Guardrails

  • Do not rewrite the artifact unless the user explicitly asks for implementation.
  • Do not invent missing business facts. Mark missing facts as required decisions.
  • Treat placeholders as acceptable in templates and suspicious in approved examples.
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. 11d ago First seen · 58 lines · 87 tokens per session scan A 9de34787128a

Subscribe to this mod's changes

audit-artifact is a skill published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 513 once invoked, about $0.0004 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.