audit

audit is a skill for Claude Code, Codex from eddiebelaval/squire. It costs 58 tokens per session (857 once invoked), scanned A, original, MIT.

A guide for building multi-agent AI workflows in which specialised agents plan tasks, use tools, maintain state, and collaborate. State means the information a workflow keeps while it runs.

In plain words
What is it for?
Use it to design agent architectures, connect tools, manage workflow state, handle errors, and add human-in-the-loop checks.
Why use it?
It helps turn loosely connected AI steps into a defined system with clear responsibilities, error handling, and human approval where needed.

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/eddiebelaval/squire/audit
Any agent
npx skills add eddiebelaval/squire --skill audit
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

Made for: Claude Code, Codex.

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/eddiebelaval/squire/audit.svg)](https://agentmods.dev/skills/eddiebelaval/squire/audit)
Your own site
<a href="https://agentmods.dev/skills/eddiebelaval/squire/audit"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 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 $0.00058 $0.00857
Opus 5 $0.00029 $0.00428
Sonnet 5 $0.00012 $0.00171
Haiku 4.5 $0.00006 $0.00086

Measured yesterday against content hash 6250e1ba9efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit - Codebase Audit

Core Workflows

Workflow 1: Primary Action

  1. Analyze the input and context
  2. Validate prerequisites are met
  3. Execute the core operation
  4. Verify the output meets expectations
  5. Report results

Run a comprehensive, read-only audit of the target codebase. Do NOT make any changes — only read, search, and report.

Arguments

/audit [scope] where scope is optional:

  • No argument: audit the current project's full codebase
  • A directory path: audit only that directory tree
  • A comma-separated list of dimensions: security,dead-code,wiring

Audit Dimensions

Run ALL dimensions by default. Use parallel Task agents (subagent_type: Explore) — one per dimension — for speed.

1. Security

  • Auth middleware on every API route (check for missing getUser() / session checks)
  • IDOR vulnerabilities: routes accepting entity IDs without ownership verification
  • Exposed secrets or env vars in client-side code
  • Missing RLS policies referenced in API routes
  • CORS and CSP configuration

2. Dead Code

  • API routes with zero frontend callers (grep for fetch/axios calls matching each route)
  • Exported functions/components with zero imports
  • Unused dependencies in package.json
  • Orphaned test files (test files whose subject no longer exists)

3. Wiring Gaps

  • UI components that render but fetch from nonexistent API endpoints
  • Store actions defined but never dispatched
  • API routes that exist but return stub/mock data
  • Event handlers wired to console.log or no-ops

4. Type Safety

  • any types, type assertions (as), and @ts-ignore / @ts-expect-error
  • Missing return types on exported functions
  • Zod schemas that don't match their TypeScript counterparts

5. UI Shells

  • Components rendering placeholder text ("Coming soon", "TODO", "Lorem ipsum")
  • Empty state components that are the only state (no real data path)
  • Hardcoded demo/mock data displayed to users

Output Format

For each finding, report:

| # | File:Line | Severity | Dimension | Finding | Suggested Fix |

Read the full file on GitHub · 99 lines

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. yesterday First seen · 99 lines · 58 tokens per session scan A 6250e1ba9efb

Subscribe to this mod's changes

audit is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 857 once invoked, about $0.0003 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 2026-09-03.