Borrowing it
Nothing to install: this file belongs to dengxu11111/dual-ai-paper-coach. 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/dengxu11111/dual-ai-paper-coach/main/.claude/skills/codex-review/SKILL.mdgit clone --depth 1 https://github.com/dengxu11111/dual-ai-paper-coachWrote 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/dengxu11111/dual-ai-paper-coach/codex-review)<a href="https://agentmods.dev/skills/dengxu11111/dual-ai-paper-coach/codex-review"><img src="https://agentmods.dev/badge/skills/dengxu11111/dual-ai-paper-coach/codex-review/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/dengxu11111/dual-ai-paper-coach/codex-review"><img src="https://agentmods.dev/badge/skills/dengxu11111/dual-ai-paper-coach/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.01955 |
| Opus 5 | $0.00026 | $0.00978 |
| Sonnet 5 | $0.00010 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
codex-review 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: codex-review
何时使用
- 用户说："让 Codex 看看"、"独立审稿"、"找盲区"、"挑刺"、"换个 AI 审一下"
- 用户跑
/codex-reviewslash command - 用户在
/iterate流程中需要新一轮审稿
核心原则（死规则）
你（Claude）从不审这份稿子。审稿是 Codex 的工作。你的角色是：
- 触发 Codex 子进程
- 等它完成
- 读它写的 review 文件
- 把内容传递给用户
如果你"自己"审，整个项目的"独立审稿"价值就毁了。
输出语言策略：发给 Codex 的 prompt 体保持英文（保证审稿报告与英文论文一致 + /iterate 命令依赖固定的英文措辞模式做替换）。中文 SKILL 说明只供人类阅读，不 影响 AI 输出。
工作流
步骤 1：环境检查
codex --version
如果失败（codex 未安装）→ 提示用户：
未检测到 Codex CLI。安装：
npm install -g @openai/codex
codex login # 用 ChatGPT Plus/Pro 账号
如果 codex login 报未认证 → 提示用户登录。
步骤 2：定位轮次号
读 my-paper/review_round_*.md，找最大 N，本次为 N+1。
第一次审稿 → N=1。
步骤 3：触发 Codex
Bash / zsh（macOS / Linux / WSL，用反斜线续行）：
ROUND=<N+1>
codex exec --skip-git-repo-check --sandbox workspace-write \
-c 'model_reasoning_effort="xhigh"' \
"Read AGENTS.md, prompts/reviewer_system.md, prompts/review_paper.md, my-paper/draft.md, and if present my-paper/data/analysis_results.json. Replace {manuscript} in review_paper.md with the contents of draft.md. If analysis_results.json is present, verify every quantitative manuscript claim against it and flag any mismatch or unverifiable number as a Critical Issue. If it is absent, state that numerical verification was unavailable. Produce a structured peer review per the format in reviewer_system.md. Write to my-paper/review_round_${ROUND}.md. Do not modify any other files."
PowerShell（Windows，用反引号续行——PowerShell 不认 \）：
$ROUND = <N+1>
codex exec --skip-git-repo-check --sandbox workspace-write `
-c 'model_reasoning_effort="xhigh"' `
"Read AGENTS.md, prompts/reviewer_system.md, prompts/review_paper.md, my-paper/draft.md, and if present my-paper/data/analysis_results.json. Replace {manuscript} in review_paper.md with the contents of draft.md. If analysis_results.json is present, verify every quantitative manuscript claim against it and flag any mismatch or unverifiable number as a Critical Issue. If it is absent, state that numerical verification was unavailable. Produce a structured peer review per the format in reviewer_system.md. Write to my-paper/review_round_$ROUND.md. Do not modify any other 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.
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.
- 12d ago First seen · 177 lines · 52 tokens per session scan A 7ece2409719a
codex-review is a skill published in the GitHub repository dengxu11111/dual-ai-paper-coach (12 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 1,955 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 2026-08-30.
Other skills, from other repositories
review-paper-code
Review research code for reproducibility and quality, extract the paper's main empirical claims, compare paper to code, and write a constructive markdown report. Designed for social science / economics projects with LaTeX papers and Stata, R, or Python code.
review-r
Read-only R code review protocol for .R scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file…
paperlab_neqsim_api_claim_verification
Verify NeqSim API references in PaperLab books against Java source, tests, notebooks, and documented setup patterns. Use for code snippets, method names, constructor signatures, units, and API claims in book chapters.
aris-experiment-bridge
Code review focused on experiment integrity, not general code quality. Check reproducibility, config-driven design, baseline fairness, seed handling. Triggers: "review experiment code", "check implementation", "bridge review", "is this code reproducible", "audit experiment implementation".
review-asi-contributions
Independently evaluate whether a SlopDotCash/asi contribution delivers a reproducible hill climb, measured research advancement or refutation, or an actual reproduced bug fix. Reject generic improvements, cleanup, and trivial work.
workflows:review
Run multi-agent econometric review on estimation code, identification arguments, and research artifacts.