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.
npx skills add Lambenthan/paper-discipline-skills --skill paper-verify-before-handoffgit clone --depth 1 https://github.com/Lambenthan/paper-discipline-skillsWrote 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/lambenthan/paper-discipline-skills/paper-verify-before-handoff)<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-verify-before-handoff"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-verify-before-handoff/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/lambenthan/paper-discipline-skills/paper-verify-before-handoff"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-verify-before-handoff.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 | $0.00190 | $0.02172 |
| Opus 5 | $0.00095 | $0.01086 |
| Sonnet 5 | $0.00038 | $0.00434 |
| Haiku 4.5 | $0.00019 | $0.00217 |
Grade A, and why
paper-verify-before-handoff 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-verify-before-handoff：交付前最后一道闸
核心理念
AI 写得太流畅会让人放松警惕。最致命的错误不是写错，是**"看起来对了所以不查了"**。 书里第 14 章的核心：对结果负责的永远是你，不是 AI——所以 AI 必须替你建一道交付闸。
完成 = 通过检查清单，不是"AI 觉得做完了"。
触发条件
满足任一条 → 触发：
- 你即将在回复里写出"改完了"、"完成了"、"已经处理好"、"可以提交"、"可以发了"
- 用户问「是不是可以了」、「还有什么要检查的吗」、「能发给导师吗」
- 你即将说「这就是最终版本」
- 一个章节 / 整篇论文的修改任务即将关闭
强制流程
你即将宣告"完成"
│
▼
立即停下，不要发出"完成"的消息
│
▼
按下方"硬检查清单"逐条核
│
▼
所有项 PASS → 把检查报告作为完成消息的一部分发出
任何一项 FAIL → 列出问题，告诉用户"还差这几条，先不能算完"
硬检查清单（必查 10 项）
| # | 项 | 怎么查 |
|---|---|---|
| 1 | 术语一致性 | grep 本次涉及的所有保护术语，确认没出现替换 |
| 2 | 引用完整性 | 所有 \cite{} / [X] 标号在参考文献里都能查到，反之亦然 |
| 3 | 数据正确 | 所有改动里的数字、百分比、年份与原始数据 / 上文一致 |
| 4 | 图表编号 | 图 1、图 2... 连续，文中"图 X"指向的图编号确实存在 |
| 5 | 内部交叉引用 | "如 §3.2 所述"、"见表 4"，引用的目标确实存在 |
| 6 | 字数 / 格式合规 | 满足 CLAUDE.md 里声明的字数 / 格式要求 |
| 7 | Todo 残留 | grep TODO / FIXME / xxx / ?? 等占位符确认全部清掉 |
| 8 | AIGC pattern（如本轮涉及文段改写 / 润色 / 通顺化） | 跑 chinese-de-aigc 五维自评，加权总分 ≥ 42 分；任何高严重度 AI 痕迹（四字套话、显性连接词、绝对化断言、隐藏被动）已修正 |
| 9 | 论证一致性（如本轮改动了核心声明） | 跑 paper-logical-consistency 扫描全文：本次改动涉及的研究问题 / 核心论点 / 假设 / 因果声明 / 边界条件 / 主要结论，在其他章节的出现都已逐处与用户确认（同步修改 / 保留原样） |
| 10 | 改动概要 | 用一句话复述改了什么、未改什么，让用户能秒判对错 |
第 8 项的"涉及文段改写"判定：本轮有任何 Edit / Write 改动了文段（不是只改格式 / 引用 / 编号 / 图表）→ 必须查。 第 9 项的"涉及核心声明"判定：本轮改动是否触及研究问题 / 核心论点 / 主要结论 / 方法边界 / 对已有研究的态度。改动了 → 必须跑；纯格式 / 引用 / 数据修订则跳过。 不是"觉得改得不多就跳过"——只要符合判定就要跑。
标准交付消息模板
改完了。交付前自查结果：
✅ 术语一致：[检查的术语列表]，无替换 ✅ 引用完整：新增 X 条引用都在参考文献里，无悬挂 ✅ 数据：[列出涉及的关键数字]，与原始一致 ✅ 图表编号：图 X、表 Y 编号连续，文中引用全部命中 ✅ 交叉引用：[列出本次涉及的 §X.X / 表 X / 图 X]，全部命中 ✅ 字数 / 格式：[当前字数 / 限制] · [格式状态] ✅ Todo：grep 无残留 ✅ AIGC pattern：chinese-de-aigc 五维评分 [具体分]（≥ 42 通过）；高严重度痕迹 [N] 处已修正 ／ 本轮未涉及文段改写，跳过 ✅ 论证一致：本次改动的核心声明 [列出] 在 §X.X / §Y.Y / §Z.Z 也出现，已逐处与用户确认 ／ 本轮未改动核心声明，跳过
本次改动概要：[一句话复述] 未触及部分：[一句话明示]
现在可以发给导师 / 提交了。
❌ 反例（书 §14.2）
用户："改完第三章给我发一份。"
错误做法：AI 改完，回："改完了，文件已保存。"
- 用户直接发给导师
- 导师两小时后回："你这个引用 [12] 在参考文献里没有"
- 用户回头查 → 发现还有三处类似问题
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 · 146 lines · 190 tokens per session scan A 4ca5bae3a440
paper-verify-before-handoff is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 4mo ago), licensed MIT. It adds 190 tokens to every session and 2,172 once invoked, about $0.0010 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
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
food-research
Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review.…
food-paper
Multi-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware throughout. Includes a…
food-pipeline
Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / food-deep-research), writing & analysis (food-paper), figures (food-figure), peer review…
food-deep-research
General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review (APA 7.0 by…
food-figure
Comprehensive figure system for food & nutrition manuscripts: analyzes the user's data, recommends the best figure(s) to make, then produces submission-grade graphics in Python or R at the target journal's spec. Handles all common scientific figure types (bar/box/violin, line/kinetic, scatter/regression, Bland–Altman…