A set of project rules and slash-command definitions for Claude Code, an AI coding assistant. The files describe commands for drafting, reviewing, revising, checking claims, and preparing a paper submission.

Use it to organize and maintain commands such as /draft, /codex-review, /iterate, /claim-check, and /finalize. It is intended for projects that prepare scientific papers and submission materials.

It keeps the paper-writing workflow consistent by defining what each command should do and which project instructions it should follow. This reduces the risk of commands containing conflicting or outdated instructions.

How dengxu11111/dual-ai-paper-coach configures Claude Code

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/.claude/commands/finalize.md

Clone the repo

git clone --depth 1 https://github.com/dengxu11111/dual-ai-paper-coach

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/finalize/github.svg)](https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/finalize)

Your own site

<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/finalize"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/finalize/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/dengxu11111/dual-ai-paper-coach/finalize"><img src="https://agentmods.dev/badge/commands/dengxu11111/dual-ai-paper-coach/finalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,180 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.02180
Opus 5	$0.00010	$0.01090
Sonnet 5	$0.00004	$0.00436
Haiku 4.5	$0.00002	$0.00218

Measured 11d ago against content hash 010ef1426b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

finalize 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 11d 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.

.claude/commands/finalize.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/finalize — 投稿草稿包生成

最终一步：把 my-paper/draft.md 打包成投稿草稿包——manuscript.docx + cover_letter.md + citations_todo.md 三件套。

⚠️ 这是草稿，不是直接 submit。你需要事后用 Web of Science 补真 DOI、填真审稿人，约 1-2 小时人工。

⚠️ 写作质量标杆：Science / Nature——cover letter 必须有 broad significance 段；AI disclosure 必须对齐 Nature 2024 / Science 2024 政策（Methods 段披露 + 提示词存档）。具体见 prompts/writer_system.md 的 "Cover letter" 段。

步骤

步骤 1：转 DOCX

直接复用 examples 示范项目里固化好的脚本 examples/global-aerosol-2010-2024/submission/_finalize_docx.py，不要每次让 Claude 重写——那份脚本已经跑通过，且做成通用模板，含投稿期刊要求的：

标题层级 → Heading 1/2/3
双倍行距（WD_LINE_SPACING.DOUBLE）
Times New Roman 12pt
行号开启（w:lnNumType continuous restart）
自动选择最新 revision_round_N.md；若没有修订稿则用 draft.md
自动扫描 my-paper/figures/ 和 my-paper/submission/figures/ 里的图片
自动读取正文、my-paper/captions.md 或 my-paper/submission/captions.md 里 Figure N. ... / Fig. N. ... 形式的 caption；没有 caption 时插入 [CAPTION_NEEDED] 占位

做法（让 Claude 执行）：

确保目录存在：my-paper/submission/

复制脚本：

cp examples/global-aerosol-2010-2024/submission/_finalize_docx.py my-paper/submission/_finalize_docx.py

Windows PowerShell 可用：

Copy-Item examples/global-aerosol-2010-2024/submission/_finalize_docx.py my-paper/submission/_finalize_docx.py

如果正文没有正式图注，先建 my-paper/submission/captions.md，每行写成 Figure 1. ... / Figure 2. ...。
直接跑脚本（不需要手改路径常量）：
```
python my-paper/submission/_finalize_docx.py
```
打开 my-paper/submission/manuscript.docx 检查：行号、双倍行距、图和 caption 是否匹配。
保留脚本不删 —— 改稿后再跑一次就出最新 docx，是"可重现产出"的一部分。

红线：不要让 Claude 从零写新脚本——会引入新 bug（行号、双倍行距、字体在 python-docx 里写法很挑），固化脚本是已经跑通的 known-good 版本。

步骤 2：列出 [CITATION_NEEDED] 占位

grep draft.md 里所有 [CITATION_NEEDED: ...] 标记，写到 my-paper/submission/citations_todo.md：

# 待补引用列表

下面这些位置需要你**手动**填真实引用（**不要让 AI 编**）。

| 位置 | 主题 | 建议搜索词 |
|---|---|---|
| §2 Introduction | aerosol-cloud indirect effect | "Twomey effect 2020-2024 review" |
| §4 Discussion | China air quality policy | "Blue Sky Defense Plan 2018 PM2.5" |
| ... | ... | ... |

Read the full file on GitHub · 146 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.

11d ago First seen · 146 lines · 19 tokens per session scan A 010ef1426b74

Subscribe to this mod's changes

finalize is a command published in the GitHub repository dengxu11111/dual-ai-paper-coach (12 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 2,180 once invoked, about $0.0001 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.

Documents PDF Writing and docs

dual-ai-paper-coach: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/finalize — 投稿草稿包生成

步骤

步骤 1：转 DOCX

步骤 2：列出 [CITATION_NEEDED] 占位

What this file has done since we first saw it

Other commands, from other repositories

open

brief-compliance-check

pipeline-minutar-pdf

docs

cti-report

cheatsheet