Borrowing it
Nothing to install: this file belongs to dewil/claude-control. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dewil/claude-control/main/.claude/skills/codex-audit/SKILL.mdgit clone --depth 1 https://github.com/dewil/claude-controlWrote 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.
[](https://agentmods.dev/skills/dewil/claude-control/codex-audit)<a href="https://agentmods.dev/skills/dewil/claude-control/codex-audit"><img src="https://agentmods.dev/badge/skills/dewil/claude-control/codex-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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 42 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 109 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Excessive Agency · line 56 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 69 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 82 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00236 | $0.09624 |
| Opus 5.5 | $0.00094 | $0.03850 |
| Sonnet 5.5 | $0.00047 | $0.01925 |
| Haiku 4.5 | $0.00024 | $0.00962 |
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 2mo 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.
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.
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.
- 2mo ago First seen · 496 lines · 236 tokens per session scan A a49fdfdc62ed
codex-audit is a skill published in the GitHub repository dewil/claude-control (10 stars, last pushed 26d ago), licensed MIT. It adds 236 tokens to every session and 9,624 once invoked, about $0.0009 per session on Opus 5.5. 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.
Other skills, from other repositories
evidence-review
Use when reviewing a substantial change against its request, or assessing code-review feedback before applying it in the current project. Skip trivial copy edits and routine status questions.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.