codex-review-gate

codex-review-gate is a skill for Codex from aaronartistzhang-afk/DailyWork. It costs 212 tokens per session (3,621 once invoked), scanned A, original, MIT.

A read-only review checkpoint that asks another coding model to inspect a plan, code change, SQL query, or externally published numbers and return a GO or NO-GO decision.

In plain words
What is it for?
It helps review implementation plans, diffs before commits, SQL before running it on a cluster, and calculations in public documents. The checkpoint does not edit files, execute changes, or commit code.
Why use it?
It adds an independent check before high-risk work is approved, deployed, committed, or shared. A failed review is repeated after the identified problems are addressed.

Skill for Codex

Written for Codex: runs codex exec. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Good fit It helps review implementation plans, diffs before commits, SQL before running it on a cluster, and calculations in public documents. The checkpoint does not edit files, execute changes, or commit code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaronartistzhang-afk/dailywork/codex-review-gate
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 aaronartistzhang-afk/DailyWork --skill codex-review-gate
Clone the repo
git clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWork

Made for: 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-review-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/codex-review-gate/github.svg)](https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/codex-review-gate)
Your own site
<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/codex-review-gate"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/codex-review-gate/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 codex-review-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/codex-review-gate"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/codex-review-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,621 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 $0.00212 $0.03621
Opus 5 $0.00106 $0.01810
Sonnet 5 $0.00042 $0.00724
Haiku 4.5 $0.00021 $0.00362

Measured 12d ago against content hash b295d5288159, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

codex-review-gate 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 12d 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/codex-review-gate/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-review-gate(跨模型只读审查门禁)

把日常口头的「老规矩」固化成一道可复用的关卡:每个高风险节点交给另一个模型(codex / GPT-5.6 Sol)在只读沙箱里独立审一遍,拿到明确的 GO / NO-GO,NO-GO 就修完重审,循环到收敛。 审查者永远不写盘、不执行、不 commit —— 门禁本身必须无副作用。

四种门禁模式plan / diff / sql / numbers)可单独调用,也可由全流程模式(老规矩)串起来。

何时用 / 不用

  • :方案定稿要过一道审查;实现完成要在 commit 前审 diff;SQL 上集群前要过 checklist;对外文档里的结论数字要逐个复算;或用户说「老规矩」要跑整条链。
  • 不用
    • 要产出 PRD / 做多视角产品决策 → 用 debate(GPT 提案 + Claude 审查的对抗式辩论,是生成器,不是门禁)。
    • 要走通用代码评审的收 / 发纪律(怎么提审、怎么消化反馈、不盲从)→ 用 requesting-code-review / receiving-code-review。本 skill 是跨模型的关卡机制,那两个是评审的行为纪律,配合使用:本 skill 决定「什么时候、用谁、审什么」,那两个决定「拿到意见后怎么做」。

调用机制(所有模式共用)

审查一律用 codex 只读沙箱、后台运行、stdin 喂审阅物:

codex exec - --sandbox read-only \
  -c model=gpt-5.6-sol \
  -c model_reasoning_effort=xhigh \
  --skip-git-repo-check
  • - :从 stdin 读 prompt / 审阅物(把方案全文、diff、SQL、数字清单 + 审查指令一起管道喂入)。
  • --sandbox read-only 显式锁死:exec 默认即 read-only + approval never,但仍显式加锁 —— 防版本漂移或 prompt 里出现「顺手改一下」被误当可写执行。门禁的铁律是零副作用:不写盘、不执行变更、不 commit。
  • -c model=gpt-5.6-sol + -c model_reasoning_effort=xhigh:跨模型(对 Claude 的盲点互补)+ 最高推理档(审查值得慢)。
  • --skip-git-repo-check:审阅物常从 stdin 来,不依赖当前目录是 git 仓库。
  • 一律后台运行:xhigh 审长文档 / 大 diff 常 >10 分钟,前台必超时。用后台任务跑,轮询结果,别阻塞主会话。
  • 失败 / 超时自动重试 1 次:第一次非零退出或超时 → 原样重投一次;再失败 → 停下报告用户(附 stderr 摘要),不要静默降级、不要假装 GO。

落盘前自检(已在 codex-cli 0.142.5 验证,装到别的机器时复核一次):跑 codex exec --help,确认 -s, --sandbox-c 存在。若某版本无 --sandbox flag,改用等效 config(如 -c sandbox_mode=read-only-c 'sandbox_permissions=[...]')并在 manifest 记录实际用法;绝不因 flag 缺失就退回可写模式

GO / NO-GO 裁决协议(所有模式共用)

每次审查的 prompt 末尾都追加这段硬要求,让机器可提取:

审完在最后一行单独输出一行裁决,格式严格为 VERDICT: GOVERDICT: NO-GO。若 NO-GO,在其上方用编号列出每一条阻断项([B1] …),每条给出:问题、证据位置、修复建议。非阻断的改进意见放在 NITS: 区,不影响裁决。

提取与循环:

  1. 抓 codex 输出最后一行 VERDICT:(正则 ^VERDICT:\s*(GO|NO-GO))。抓不到 → 视为审查未完成,按「失败重试 1 次」处理;重试仍抓不到 → 报告用户,人工判读。
  2. GO → 本模式通过,进入下一步(或结束)。
  3. NO-GO → 把编号阻断项逐条落改(最小改动半径,一条一条来),改完把新版本 + 上一轮阻断清单 + 逐条修复说明重新喂 codex 复审。
  4. 循环上限 3 轮:第 3 轮仍 NO-GO(或阻断项在打转、来回反复不收敛)→ 停下升级问用户,附三轮裁决摘要 + 当前未闭合阻断项,请用户裁断(是真问题、还是 codex 误判、还是要调方案)。绝不无限刷。

Read the full file on GitHub · 156 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 156 lines · 212 tokens per session scan A b295d5288159

Subscribe to this mod's changes

codex-review-gate is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 14d ago), licensed MIT. It adds 212 tokens to every session and 3,621 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

isolating-product-facade-contracts

Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still exposes internals (models/logic/views) across boundaries and needs migration toward contracts.py + facade/api.py + presentation separation, with a PR strategy…

PostHog/posthog · 76 tokens

qa-frontend

Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…

PostHog/posthog · 142 tokens

reviewing-personhog-protocol

The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog semantics. Use before pushing or requesting review on any personhog protocol changeset, when asked for an exhaustive or careful review of personhog code, and after any…

PostHog/posthog · 111 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog · 197 tokens

extending-hobby-smoke-tests

Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…

PostHog/posthog · 83 tokens

writing-code-comments

Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any language (Python, TypeScript, Go, Rust, SQL), and when reviewing a diff that adds comments. Removes the comment types that clutter the codebase: narration that…

PostHog/posthog · 173 tokens