dual-ai-paper-coach: Command for Codex

.codex/prompts/review.md

review is a command for Codex from dengxu11111/dual-ai-paper-coach. It costs 0 tokens per session (818 once invoked), scanned A, original, MIT.

A command template for producing an independent review of a research paper. It tells an AI reviewer which project files to read, how to verify numerical claims, and where to save the next review report.

In plain words
What is it for?
Use it to review a manuscript draft, check reported figures against analysis results, assign a verdict, and save sections such as critical, important, minor, and wording issues.
Why use it?
It gives paper reviews a consistent structure and helps catch unsupported or incorrect numbers without relying on the paper writer’s instructions.

Command for Codex

Written for Codex: installed under .codex/. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is dengxu11111/dual-ai-paper-coach's own configuration. It tells Codex how to work on dual-ai-paper-coach itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dual-ai-paper-coach configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/dengxu11111/dual-ai-paper-coach/main/.codex/prompts/review.md
Clone the repo
git clone --depth 1 https://github.com/dengxu11111/dual-ai-paper-coach

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/review/github.svg)](https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/review)
Your own site
<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/review"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/review"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 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 $0.00000 $0.00818
Opus 5 $0.00000 $0.00409
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 12d ago against content hash 2e415a5c8e24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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.

.codex/prompts/review.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex 审稿模板(备用)

这份是直接在 Codex CLI 里跑的 prompt 模板。 正常流程是 Claude Code 通过 /codex-review 自动调用;如果你想绕过 Claude 直接让 Codex 审,可以手动用这份 prompt。

输出语言策略:审稿报告强制英文(与论文一致 + /iterate 命令依赖固定的 英文措辞模式做替换)。中文说明只用于人类阅读流程,不影响 AI 输出。

用法(手动 REPL)

⚠️ 务必在项目根目录(含 AGENTS.md 的目录)启动 codex,不要 cd 进 my-paper/——否则路径会错。

# 在项目根目录(不是 my-paper/)执行
codex

进入 Codex REPL 后粘贴:


读以下文件并按照 reviewer_system.md 的格式产出结构化审稿报告:

  1. AGENTS.md —— 你的工作守则
  2. prompts/reviewer_system.md —— 审稿系统准则
  3. prompts/review_paper.md —— 任务模板({manuscript} 替换为 draft.md 的内容)
  4. my-paper/draft.md —— 当前论文
  5. my-paper/data/analysis_results.json(如果存在)——数字核验来源

输出:

  • 审稿报告写到 my-paper/review_round_<N>.md(N 是新的轮次号,看 my-paper/review_round_*.md 已存在的最大 N+1)
  • 不要修改任何其他文件
  • 不要去看 prompts/writer_system.md(那会污染你的独立性判断)
  • 如果 analysis_results.json 存在,逐条核对论文里的定量数字;对不上或找不到的数字写成 Critical Issue
  • 如果 analysis_results.json 不存在,明确写 "numerical verification was unavailable"

按 reviewer_system.md 的格式输出 Score / Summary / Critical / Important / Minor / Wording / Verdict。


用法(一次性 exec)

在项目根目录跑。

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. The {manuscript} placeholder in review_paper.md should be replaced with draft.md content. 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 reviewer_system.md format. Write to my-paper/review_round_<N>.md. Do not modify other files."

关键参数(缺一就会卡):

  • --skip-git-repo-check — 避免 Codex 卡 git repo 检查
  • --sandbox workspace-write必须,默认沙盒只读 Codex 写不进 review_round_N.md
  • -c 'model_reasoning_effort="xhigh"' — 审稿要 xhigh,默认 medium 漏问题

Read the full file on GitHub · 64 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. 12d ago First seen · 64 lines · 0 tokens per session scan A 2e415a5c8e24

Subscribe to this mod's changes

review is a command published in the GitHub repository dengxu11111/dual-ai-paper-coach (12 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 818 tokens. 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.