audit

audit is a skill for Claude Code from odere-pro/claude-oop-excellence. It costs 184 tokens per session (2,749 once invoked), scanned A, original, MIT.

A read-only codebase review that checks software quality, risks, and design patterns. It can examine the whole project, changed files, or a selected component.

In plain words
What is it for?
Use it before releases, after large pull requests, or when learning an unfamiliar project. It can find code smells and vulnerabilities, and identify or suggest design patterns.
Why use it?
It gives one way to find code problems, security and dependency risks, and design issues without changing the code.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the claude-oop-excellence plugin — 5 skills, 2 commands, 6 agents, 1 hook shipped together

Good fit Use it before releases, after large pull requests, or when learning an unfamiliar project. It can find code smells and vulnerabilities, and identify or suggest design patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odere-pro/claude-oop-excellence/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 odere-pro/claude-oop-excellence --skill audit
Clone the repo
git clone --depth 1 https://github.com/odere-pro/claude-oop-excellence

Made for: Claude Code.

Or install claude-oop-excellence, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 6 agents, 1 hook.

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/odere-pro/claude-oop-excellence/audit/github.svg)](https://agentmods.dev/skills/odere-pro/claude-oop-excellence/audit)
Your own site
<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/audit"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/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.

agentmods 80×15 button for audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/odere-pro/claude-oop-excellence/audit"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-oop-excellence/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,749 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 $0.00184 $0.02749
Opus 5 $0.00092 $0.01375
Sonnet 5 $0.00037 $0.00550
Haiku 4.5 $0.00018 $0.00275

Measured 8d ago against content hash f0a7c37273f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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 · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality, Risk & Design Audit

/audit is THE read-only analysis entry point for this plugin. It subsumes every separate analysis path — there is one front door, one selector grammar, and one unified report. It resolves a selector against the glossary, delegates the heavy lifting to the oop-orchestrator, and returns a single merged report. It assumes nothing about the language or stack and never modifies code.

The plugin organizes analysis across two tracks and zooms through three layerstrack → aspect → family / category / entity:

  • RISK track — find problems: code smells, antipatterns, vulnerabilities, supply-chain risks.
  • PATTERN track — work with design patterns: detect patterns already present (pattern-scan) and suggest the most-suitable patterns where one would help (pattern-fit).

A full /audit runs both tracks in parallel and merges them into ONE report.

Selector grammar

/audit [full | changed | component <path>]            → L1: both tracks, in parallel, one report
/audit risks [scope]                                  → L2: RISK track only
/audit patterns [scope]                               → L2: PATTERN track (scan + fit)
/audit pattern-scan [scope]                           → aspect: patterns already present
/audit pattern-fit [scope]                            → aspect: most-suitable pattern suggestions
/audit <category> [scope]                             → one issue/pattern category
/audit <family> [scope]                               → one family of issues or patterns
/audit <entity-id> [scope]                            → one entity or pattern

Every form takes an optional scope suffix — full (default), changed, or component <path>.

What to look for (selector, default = both tracks)

The glossary is the single source of truth for what the plugin recognizes. A selector resolves against it, zooming from the broadest layer (a whole track) to the narrowest (one entity):

  • full / changed / component <path> / none — the L1 full run: the RISK track and the PATTERN track dispatched in parallel, merged into one unified report. (A bare scope word with no selector is the full run scoped accordingly.)
  • risks — the RISK track only (its sole aspect is risk-scan): every issue family (oop, code, architecture, testing, concurrency, database, security, dependency).
  • patterns — the PATTERN track: both aspects, pattern-scan + pattern-fit.
  • pattern-scan — one aspect: design patterns already present in the code.
  • pattern-fit — one aspect: the most-suitable patterns where one would help.
  • <category> — one category of entities (e.g. vulnerability, antipattern, code-smell, supply-chain-risk, design-pattern).
  • <family> — one family of issues or patterns (e.g. oop, security, behavioral). oop is the spine of this plugin — it surfaces whenever class/struct/interface declarations are present.
  • <entity-id> — a single glossary entity or pattern, by its stable id (e.g. god-class, feature-envy, strategy).

Read the full file on GitHub · 194 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. 8d ago First seen · 194 lines · 184 tokens per session scan A f0a7c37273f4

Subscribe to this mod's changes

audit is a skill published in the GitHub repository odere-pro/claude-oop-excellence (1 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,749 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.