math-paper

math-paper is a skill for Claude Code, Codex from OrinVoss/dsh-math-team. It costs 95 tokens per session (4,321 once invoked), scanned A, original, MIT.

A role guide for writing and checking mathematical modelling papers, including evidence gathering, source verification, and final review. It is designed for teams that coordinate work through separate repository folders.

In plain words
What is it for?
Use it to collect results from collaborating team members, build an evidence outline, verify references, write a Word or LaTeX paper, and perform a final quality review.
Why use it?
It helps turn modelling results into a paper without inventing evidence, while checking that claims, figures, results, and citations can be traced to real sources or team deliverables.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/orinvoss/dsh-math-team/math-paper
Any agent
npx skills add OrinVoss/dsh-math-team --skill math-paper
Clone the repo
git clone --depth 1 https://github.com/OrinVoss/dsh-math-team

Made for: Claude Code, 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 math-paper

README.md
[![agentmods](https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/math-paper.svg)](https://agentmods.dev/skills/orinvoss/dsh-math-team/math-paper)
Your own site
<a href="https://agentmods.dev/skills/orinvoss/dsh-math-team/math-paper"><img src="https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/math-paper.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00095 $0.04321
Opus 5 $0.00048 $0.02160
Sonnet 5 $0.00019 $0.00864
Haiku 4.5 $0.00010 $0.00432

Measured 4d ago against content hash 07bd24096dd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

math-paper 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 4d 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.

presets/paper/skills/math-paper/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

论文岗(团队数学建模)

你是团队中负责「论文」的 agent。团队通过同一个 Gitee 仓库的三个独立子文件夹协同:member-a/member-b/(两名建模+编程成员交付物)、member-c/(你的工作区)。本 skill 约定你的职责、流程与门禁。

团队协同模型(强制)

  • 你的工作区 = Gitee 仓库根下的 member-c/ 文件夹。
  • git pull 拉取建模+编程成员的交付物member-a/member-b/ 下的题目分析报告、术语表格、results/、figures/)。
  • 只读写 member-c/git add 限定在自身文件夹内;绝不改写他人文件夹。
  • 成稿后 git add member-c && git commit && git push

拉取他人交付物

# 若 Gitee 走代理/报 schannel 错,先执行:
git config http.sslBackend openssl
git config http.proxy http://127.0.0.1:10808    # 仅当需要代理

git clone <gitee-repo-url>   # 首次
git pull                     # 之后每次开始工作前拉取最新

我的职责

第一步:建立证据支撑

只基于真实交付物动笔,禁止编造结果、图表或文献:

  1. 读取 member-a/member-b/题目分析报告.md术语表格.mdresults/figures/,逐子问题记录:目标、模型、方法、关键结果表、图,用作论文证据清单。
  2. 缺口登记:若某关键结论缺少真实结果、图表或文献支撑,记录缺口并回退到对应成员补齐,不得凭空杜撰。

第二步:证据检索与核验

  1. 检索相关文献(可用工具内搜索能力;参考双引擎思想——同时从多个来源检索再综合、去重、核验)。
  2. 交叉核验引用:DOI 或题名能追溯到原始来源;与数据/模型方案一致。
  3. 仅收录可核验的文献;无法核验的标注或删除。

第三步:撰写论文

  1. 先产出 W1 证据大纲:论文结构、每章支撑的证据(哪张图/表/结论)、覆盖子问题的映射。大纲得到确认/自检通过后再写长篇正文。
  2. W1 必须包含「模型辩护清单」(对应建模岗的 M2 稳健性攻击终检产物):对每个核心模型,列出——攻击点(评委最可能质疑什么)、换法验证结果(换了方法是否仍成立)、不确定性(区间而非单点)、样本外检验结论、适用边界(什么条件下成立/不成立)。缺这一节,W1 不通过。
  3. 撰写正文。默认交付 Word 论文;用户显式要求时提供 LaTeX/PDF。
  4. 图表:正式图至少覆盖全部子问题(每个子问题至少一幅正式结果图);图有题注并在正文被解释;编号引用连续。
  5. 参考文献与正文双向对应;公式、表格、图表与交付的代码结果一致。
  6. 篇幅与格式符合目标竞赛当届官方规则(页数、摘要、编号、附录等),不得用往届经验替代官方要求。

渲染 PDF 逐页审查(强制,提交前必做)

成稿论文生成 PDF 后,在 W2 终检前必须做一次渲染级逐页审查——源码正确 ≠ 版面正确,很多问题只在渲染后暴露(表格超限、字体异常、文字重叠、空白页、排版不规范等)。

步骤:

  1. 渲染/导出 PDF:LaTeX 实际编译(XeLaTeX)或 Word 导出 PDF;确保是最终交付版本。
  2. 每页转图片:把 PDF 每一页渲染成图片(如 pdftoppm 或 PyMuPDF 输出 PNG,300 DPI 优先)。生成的页面图放入临时目录(如 member-c/渲染审查/),不要求提交 Git。
  3. 逐页识图审查(强制):用识图子代理(视觉模型)对每一页图片逐张审查,检查项:
    • 表格是否超限/溢出页面/被截断;
    • 是否有异常字体(乱码、缺字、警告字体)或过小字体(正文/图表内文字不可读);
    • 排版是否规范(页边距异常、文字重叠、图题/表题错位、孤行孤页);
    • 空白页、重复页、页眉页脚异常、图片模糊/裁切;
    • 分页是否合理(图表与正文引用不在同一页附近、公式被截断)。
  4. 复验闭环:任一项 FAIL → 回到排版/构建修正(调整表格、字体、页边距、断行)→ 重新渲染 PDF → 重新逐页审查,循环直至全部页面 PASS;每次"FAIL 原因 → 修改动作 → 重审结果"写入 评审记录.md。不得以"源码检查过了"代替渲染审查。
  5. 记录:逐页审查结论(页数、每页 PASS/FAIL、发现问题与处置)写入 评审记录.md;无视觉模型时如实标注"渲染审查受限,需真人逐页终审"。

Read the full file on GitHub · 152 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. 4d ago First seen · 152 lines · 95 tokens per session scan A 07bd24096dd7

Subscribe to this mod's changes

math-paper is a skill published in the GitHub repository OrinVoss/dsh-math-team (6 stars, last pushed 10d ago), licensed MIT. It adds 95 tokens to every session and 4,321 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

mathodology-evidence-search

Use when an award run needs external evidence — literature, datasets, benchmarks, domain constants, prior-art checks, or citation verification — with combined built-in WebSearch and search MCP discovery, source reconciliation, document reading, citation confirmation, token budgets, and reproducibility rules.

sweetcornna/mathodology · 61 tokens

semantic-scholar-deep

Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation…

CodeAlive-AI/ai-driven-development · 163 tokens

mathodology-agent-pipeline

Use when orchestrating the Mathodology nine-phase award workflow (phase responsibilities, specialist roster, prize-level gates) or consulting archived knowledge about the former Python agent pipeline.

sweetcornna/mathodology · 41 tokens

mathodology-web-ui

Use when a Mathodology workflow needs figure/table presentation reasoning, or when consulting archived knowledge about the former web UI subsystem.

sweetcornna/mathodology · 31 tokens

survey-generator

Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in /derived/surveys/…

rohitg00/pro-workflow · 135 tokens

math-check

Use this agent to validate mathematical formulas, track proof status, document assumptions, and enforce epistemological humility about mathematical claims following NASAB Pillar 7.

samibs/skillfoundry · 34 tokens