codex-audit

codex-audit is a skill for Claude Code, Codex from dewil/claude-control. It costs 236 tokens per session (9,624 once invoked), scanned A, original, MIT.

A read-only workflow that asks the Codex command-line tool for an independent review of code, a plan or a proposed change. It supports detailed review, deliberate attempts to break a solution, a second opinion, plan-compliance checks and diagnosis when work is stuck.

In plain words
What is it for?
Use it to audit code or a diff, attack a design, compare approaches, check implementation against a plan, or investigate a problem. Reports and review plans are stored in the repository's docs/dev directory.
Why use it?
It gives the main coding agent another viewpoint without allowing that reviewer to change repository files. This can expose risks, blockers, missed requirements or failure cases before changes are accepted.

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/dewil/claude-control/codex-audit
Any agent
npx skills add dewil/claude-control --skill codex-audit
Clone the repo
git clone --depth 1 https://github.com/dewil/claude-control

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 codex-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/dewil/claude-control/codex-audit.svg)](https://agentmods.dev/skills/dewil/claude-control/codex-audit)
Your own site
<a href="https://agentmods.dev/skills/dewil/claude-control/codex-audit"><img src="https://agentmods.dev/badge/skills/dewil/claude-control/codex-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 236 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00236 $0.09624
Opus 5 $0.00118 $0.04812
Sonnet 5 $0.00047 $0.01925
Haiku 4.5 $0.00024 $0.00962

Measured 4d ago against content hash a49fdfdc62ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-audit scanned grade A with 1 finding 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 4d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. **Всегда** явно фиксировать модель и effort в команде, не полагаться на `~/.codex/config.toml`:

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/codex-audit/SKILL.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-audit

Скилл для делегирования в codex CLI на этой машине задач, требующих другой модели как независимого второго взгляда, без права что-либо менять в репо (read-only). Codex изолирован: не видит контекст текущей сессии Claude, но читает файлы репозитория. Ценность не в том, что он "умнее" - а в разнообразии мышления: другая модель ловит другие классы ошибок, чем основной агент.

Режимы

Режим Когда Effort Формат ответа Codex Файлы в docs/dev/
audit (дефолт) глубокий разбор кода/диффа/плана; "отправь на аудит", "пусть codex проверит" high по каждому вопросу вердикт ok / risk / blocker + 1-2 предложения audit-plan-<topic> / audit-report-<topic>
adversarial состязательное ревью со скептической позицией; "сломай решение", "состязательное ревью", "попробуй сломать через codex" - нужно не подтверждение, а активный поиск дыр high по каждому компоненту: чем и при каких условиях сломается; "проблем нет" - только с перечнем проверенных атак adversarial-plan-<topic> / adversarial-report-<topic>
second-opinion независимый взгляд на подход/решение/дифф; "второе мнение", "посоветуйся"; по умолчанию после крупной работы medium согласен / не согласен + альтернативы + трейдоффы (не чеклист блокеров) consult-plan-<topic> / consult-report-<topic>
compliance сверка реализации с исходным планом; "проверь, что реализовал план", "сверь дифф с планом" - что сделано, что пропущено, что добавлено сверх плана medium таблица "пункт плана -> статус (реализовано / частично / пропущено / отклонено) -> комментарий" + блок "сверх плана" compliance-plan-<topic> / compliance-report-<topic>
escalation основной агент застрял (3+ провалившихся фикса, гипотезы не подтверждаются, субагент BLOCKED) - до похода к человеку high диагноз + root cause с доказательствами + рекомендованный подход escalate-plan-<topic> / escalate-report-<topic>

Общая обвязка одинакова во всех режимах: запуск через codex exec -s read-only, фиксация -C <project-root>, модель gpt-5.5, pre-check и пост-сбор лимитов, блок про субагентов в плане, требование к Codex писать session id первой строкой отчета. Различаются только effort, фрейминг плана/промпта, формат ответа и имена файлов.

Read the full file on GitHub · 496 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. 4d ago First seen · 496 lines · 236 tokens per session scan A a49fdfdc62ed

Subscribe to this mod's changes

codex-audit is a skill published in the GitHub repository dewil/claude-control (10 stars, last pushed 6d ago), licensed MIT. It adds 236 tokens to every session and 9,624 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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

clawdline

Use Clawdline to dispatch a bounded child task when the current Root keeps synthesis, integration, and landing; to hand off an existing work line for full continuation; or to send a message, report, status, finding, or coordination note to another live session. Triggers include "dispatch a task", "open a child…

sainteye/clawdline · 218 tokens

hermes-memory-github-sync

Set up automatic GitHub sync for Hermes Agent memory, skills, and config using git + macOS launchd. Runs every 30 minutes in the background. Covers repo init, .gitignore pitfalls, token extraction, and launchd plist setup.

itgoyo/hermes-skills · 57 tokens

hermes-memory-github-sync

Set up automatic GitHub sync for Hermes Agent memory, skills, and config using git + macOS launchd. Runs every 30 minutes in the background. Covers repo init, .gitignore pitfalls, token extraction, and launchd plist setup.

itgoyo/multica-skills · 57 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

spinabot/brigade · 20 tokens

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…

vellum-ai/vellum-assistant · 90 tokens