audit

audit is a skill for Claude Code, Codex from MichaelYcJo/SpecSeal. It costs 77 tokens per session (499 once invoked), scanned A, original, MIT.

A project-specific rule checker that reads Markdown files in `.claude/audit-rules/` and checks whether the code follows them. These rules cover conventions unique to a repository, beyond what a standard linter checks.

In plain words
What is it for?
Use it before a commit or release to validate repository-specific patterns, such as restrictions on secrets, logging, or unfinished TODO items.
Why use it?
It catches agreements the project has written down but ordinary formatting or code-quality tools cannot enforce. If no rule files exist, it reports that instead of treating suggested conventions as requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the specseal plugin — 23 skills, 3 agents, 3 hooks shipped together

Good fit Use it before a commit or release to validate repository-specific patterns, such…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michaelycjo/specseal/audit
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 MichaelYcJo/SpecSeal --skill audit
Clone the repo
git clone --depth 1 https://github.com/MichaelYcJo/SpecSeal

Made for: Claude Code, Codex.

Or install specseal, the plugin that ships this one along with the rest of its 23 skills, 3 agents, 3 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/michaelycjo/specseal/audit.svg)](https://agentmods.dev/skills/michaelycjo/specseal/audit)
Your own site
<a href="https://agentmods.dev/skills/michaelycjo/specseal/audit"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00077 $0.00499
Opus 5 $0.00039 $0.00249
Sonnet 5 $0.00015 $0.00100
Haiku 4.5 $0.00008 $0.00050

Measured 6d ago against content hash 6723926ab60b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

skills/audit/SKILL.md · 62 lines

What it actually says

audit — the rules this repo wrote down for itself

A linter enforces what every project agrees on. This checks what only this project agreed on, declared as .claude/audit-rules/*.md. A rule with no file behind it is not a rule; if the directory is empty, say so rather than inventing conventions.

How It Works

  1. Check for rules: Look for .claude/audit-rules/*.md files
  2. If no rules exist: Suggest bootstrapping with common patterns
  3. If rules exist: Validate each rule against the codebase

Rule File Format

Each .claude/audit-rules/[name].md defines:

  • Pattern: What to check (regex, file pattern, or description)
  • Expected: What should be true
  • Severity: critical / warning / info

Common starting rules

Nothing here runs on its own. These are what to propose when .claude/audit-rules/ is empty (step 2), and each one becomes a rule only once it is written as a file:

  • No hardcoded secrets (API keys, passwords, tokens)
  • No console.log in production code (unless a logging library wraps it)
  • No TODO/FIXME in the code being committed

Managing rules

There is no audit command to run. A rule is a file, so adding one means writing .claude/audit-rules/<name>.md, listing them means reading that directory, and removing one means deleting the file.

Output Format

## Audit Results

✅ Passed: [N] rules
⚠️ Warnings: [N]
❌ Violations: [N]

[For each violation:]
❌ [rule name] - [severity]
   [file:line] [what's wrong]
   Fix: [suggestion]
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. 6d ago First seen · 62 lines · 77 tokens per session scan A 6723926ab60b

Subscribe to this mod's changes

audit is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 499 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.