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-logical-consistencygit 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-logical-consistency)<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-logical-consistency"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-logical-consistency/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-logical-consistency"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-logical-consistency.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 | $0.00155 | $0.01857 |
| Opus 5 | $0.00077 | $0.00928 |
| Sonnet 5 | $0.00031 | $0.00371 |
| Haiku 4.5 | $0.00015 | $0.00186 |
Grade A, and why
paper-logical-consistency 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-logical-consistency：论证一致性
核心理念
论文不是字符的拼接，是论证链的组合。改一处核心论点，前后章节里同概念的出现都要回查——但人累了、赶时间最容易跳过，AI 改完也不会自己想起。
改一个观点，不是改一段话；改一段话，可能动了整篇论证的脊柱。
触发条件
满足任一条 → 触发：
- 用户改动「研究问题」「核心假设」「主要结论」「因果机制」
- 用户改动方法描述（边界条件 / 关键参数 / 适用范围）
- 用户对已有研究 / 竞品的批评力度变化
- 用户改动数据的解释（不是数据本身）
- 用户提到「我把 §X.X 的 [核心概念] 改了」
- 用户在交付前要求「检查一下逻辑」「看看有没有矛盾」
强制流程
检测到核心声明改动
│
▼
提取本次改动的「核心声明锚点」：
- 研究问题 / 假设的关键短语
- 因果关系的主词谓词宾语
- 方法的边界条件 / 关键参数
- 对已有研究 / 竞品的态度词
│
▼
grep / 全文搜索这些锚点的出现位置
（不只是逐字匹配，还要语义同义词）
│
▼
列出每个出现位置的上下文片段：
- §X.X 第 Y 段：「...原文摘录约 50 字...」
│
▼
告诉用户：「下面这些位置提到了同一概念，
本次改动后是否需要联动修改？」
│
▼
等用户对每处给出 ✅同步改 / ❌保持原样 / ❓我看一下
│
▼
按用户决定执行
完成后由 paper-verify-before-handoff 第 9 项「论证一致性」复核
标准回复模板
你这次改的是 [核心声明摘要]。我扫描了全文，下面 N 处提到了同一概念：
§1.2 第 3 段：「...原文摘录...」 → 这里说的是改前的版本，是否要同步？
§4.5 第 1 段：「...原文摘录...」 → 这里是结论部分，目前还在回答改前的研究问题。
§5.1 引言：「...原文摘录...」 → 这里复述了你的论点，措辞需要重新对齐吗？
请你逐条回复 ✅同步 / ❌保留 / ❓我看一下，再决定下一步。
提取「核心声明锚点」的规则
| 改动类型 | 抓什么作锚点 |
|---|---|
| 研究问题 | 关键短语（"是否影响"、"通过 X 影响 Y"） |
| 因果机制 | 主词 + 谓词 + 宾语三元组 |
| 方法边界 | 边界条件 / 适用范围 / 关键参数 |
| 主要结论 | 结论的核心断言（强 / 弱 / 条件） |
| 对已有研究态度 | 评价词（支持 / 反对 / 修正 / 扩展） |
| 假设 | 假设的强弱程度词 |
锚点提取后，用 grep + 语义同义词扩展（同一概念的不同表述）做全文扫描。
❌ 反例
用户：「我把 §3.2 的研究问题从『XX 是否影响 YY』改成『XX 通过 ZZ 影响 YY』。」
错误做法：AI 只改了 §3.2 那一段，paper-verify-before-handoff 跑完前 9 项硬清单全 ✅，告诉用户「改完了」。
- §1.4 摘要还说「研究 XX 是否影响 YY」
- §4.5 结论还在讨论「XX → YY 的直接影响」
- §5.3 讨论部分又开始扯 ZZ
- 导师一眼看出：摘要、研究问题、结论自相矛盾
正确做法：扫出 §1.4 / §4.5 / §5.3 三处提到同概念的位置，列出来让用户决定每处是否联动改。
与 paper-protect-terminology 的差别
| paper-protect-terminology | paper-logical-consistency | |
|---|---|---|
| 抓什么 | 术语字符没被改 | 概念语义保持一致 |
| 检查方式 | grep 字符串 | 阅读上下文判断语义 |
| 谁来判断 | AI（用 grep 数数） | 用户（AI 只列疑点） |
| 例 | 「BERT」没被改成「伯特」 | §3.2 说「XX 通过 ZZ 影响 YY」，§4.5 也是这个表述 |
两者互不替代，各管各的事。
Rationalization Table
| 念头 | 现实 |
|---|---|
| "用户只让我改 §3.2，其他章节不该动" | 用户没意识到要联动改，AI 必须主动扫出来给他看 |
| "改一个研究问题，应该不影响其他段落" | 研究问题是论证链的源头，下游全部受影响 |
| "全文搜索太重，差不多就行" | 漏一处就是论证穿帮，导师一句"前后矛盾"全要返工 |
| "只看保护词术语就够" | 术语一致 ≠ 论证一致；术语没换但语义可能已经矛盾 |
| "我能从 grep 结果直接判断哪些要改" | 不能。语义判断必须用户做，AI 只负责"找疑点 + 呈现给用户" |
| "用户最后会自己复审，我不用扫" | 用户复审容易漏，本 Skill 是给 AI 的纪律，不是给用户的提议 |
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 · 161 lines · 155 tokens per session scan A 717af25ff80a
paper-logical-consistency is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 4mo ago), licensed MIT. It adds 155 tokens to every session and 1,857 once invoked, about $0.0008 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…