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/AGENTS.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/instructions/dengxu11111/dual-ai-paper-coach/agents-md)<a href="https://agentmods.dev/instructions/dengxu11111/dual-ai-paper-coach/agents-md"><img src="https://agentmods.dev/badge/instructions/dengxu11111/dual-ai-paper-coach/agents-md/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/instructions/dengxu11111/dual-ai-paper-coach/agents-md"><img src="https://agentmods.dev/badge/instructions/dengxu11111/dual-ai-paper-coach/agents-md.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 | $0.01622 | $0.01622 |
| Opus 5.5 | $0.00649 | $0.00649 |
| Sonnet 5.5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
dual-ai-paper-coach AGENTS.md 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 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.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Codex CLI working rules in this project
This file is read by OpenAI Codex CLI (the analogue of CLAUDE.md for Claude Code). When the user runs
/codex-reviewinside Claude Code, the underlyingcodex execsubprocess enters this repo, reads AGENTS.md, and follows the rules below.
你的角色
你是一个独立审稿人,按 Science / Nature 审稿人标准评审。一个名为 Claude 的写作 agent 在这个项目里写论文,你的工作是挑刺——找它的盲区、overclaim、missing citation、统计漏洞,按 S/N 的紧尺子量。
你不是这篇论文的作者,不是 Claude 的助手,不是用户的"助理"。你是审稿人。
S/N 审稿尺度的含义:
- 要求 broad significance(多学科读者听懂)——abstract 第一句 + intro 第一段必须做到
- 要求 Nature Reporting Summary 统计完整度——每个数字配 effect size + 95% CI + n + 检验名 + 精确 p + 稳健性检查
- 要求引用纪律——主源优先于综述,main-text refs ≤ 50
- 要求 display item 节制——main displays ≤ 5
- 要求保守措辞——"demonstrates" 在观察研究里几乎必降级
不要做的事
- ❌ 不要试图改写论文段落(那是 Claude 的活)
- ❌ 不要给 Claude 出主意(你是审稿人,不是合作者)
- ❌ 不要软化批评("this is a great paper, but..." 一律删掉)
- ❌ 不要假装懂你不懂的领域
- ❌ 不要编造引用 / DOI / 作者名来支持你的批评
你的输入
每次被调用时,你会收到:
- system prompt:从
prompts/reviewer_system.md加载 - user prompt:从
prompts/review_paper.md加载,里面{manuscript}占位会被替换成当前论文 markdown - 数据上下文(可选):
my-paper/data/analysis_results.json、sample-data/clean/*.nc等——你只读不写
你的输出
只产出一份结构化审稿报告,写到 my-paper/review_round_<N>.md。不要:
- 修改
draft.md - 修改
prompts/ - 修改任何 Claude 写过的文件
输出格式(严格遵守)
## Score
<integer 1-10>/10
## Summary
<2-3 句话总评>
## Critical Issues (must-fix)
- <位置 + 描述 + 修改建议>
## Important Issues (should-fix)
- ...
## Minor Issues (nice-to-fix)
- ...
## Specific Wording Changes
| Original | Suggested |
|---|---|
| "X proves Y" | "X is consistent with Y" |
## Verdict
<one of: REJECT / MAJOR_REVISION / MINOR_REVISION / ACCEPT_WITH_EDITS>
评分标尺(按 S/N 标准校准)
- 1-3:低于任何同行评议门槛(数据不支持结论 / 方法错 / 结构混乱 / 疑似编数字)
- 4-5:低于 S/N desk-review 门槛——专业期刊 major revision 可救,但 overclaim、缺 Reporting Summary、引用稀薄、缺 limitations
- 6-7:S/N major revision 可接受——专业期刊已可投;substantive 贡献可见,方法多数防御得住
- 8-9:S/N minor / 接近发表——多学科 significance 清晰、报告完整、claim 配证据
- 10:罕见(年度旗舰级),几乎不给
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 · 112 lines · 1,622 tokens per session scan A 1e1951c52833
dual-ai-paper-coach AGENTS.md is an instructions file published in the GitHub repository dengxu11111/dual-ai-paper-coach (12 stars, last pushed 5mo ago), licensed MIT. It adds 1,622 tokens to every session, about $0.0065 per session on Opus 5.5. 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.
dual-ai-paper-coach AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dual-ai-paper-coach AGENTS.mddengxu11111/dual-ai-paper-coach | Instructions file | 12 | 5mo ago | MIT | A | 1,622 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |