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 LiXiang106991/MathModelAgent --skill mcm-model-typesetgit clone --depth 1 https://github.com/LiXiang106991/MathModelAgentWrote 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/lixiang106991/mathmodelagent/mcm-model-typeset)<a href="https://agentmods.dev/skills/lixiang106991/mathmodelagent/mcm-model-typeset"><img src="https://agentmods.dev/badge/skills/lixiang106991/mathmodelagent/mcm-model-typeset/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/lixiang106991/mathmodelagent/mcm-model-typeset"><img src="https://agentmods.dev/badge/skills/lixiang106991/mathmodelagent/mcm-model-typeset.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 | $0.00065 | $0.01479 |
| Opus 5 | $0.00032 | $0.00740 |
| Sonnet 5 | $0.00013 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
mcm-model-typeset 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 today.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
优化类建模章节排版规范
本 skill 只规定章节结构与句式。全部公式内容、符号含义、数值一律 来自用户提供的材料;禁止自行发明符号、口径或修改任何数字。
M1 五段式章节骨架
每个问题固定为:
\subsection{问题X模型的建立与求解}
\subsubsection{决策变量的确定}
\subsubsection{目标函数} % 标题措辞可随材料调整
\subsubsection{约束条件}
\subsubsection{模型汇总}
\subsubsection{求解} % 可选
- 标题为 4–10 字名词短语,不带句号;
- 多问题时其余问题沿用同构骨架,编号递增。
M2 符号定义三段式
每个新公式按「引入句 → 公式 → 符号说明」三段式:
- 引入句:一句话交代本段定义什么,以",设:"或冒号收尾;
- 公式:
equation环境,右侧编号; - 符号说明段:以"其中,"开头,各符号解释用分号连排,
末项以句号收尾;每项格式:
符号 表示 含义(单位);- 指标取值范围(年、编号等)写在符号说明段内,不独立成段;
- 禁止改用表格或 bullet 列表;
- 符号在首次出现处解释,后文直接使用不再解释。 若一个公式说明完后需要引出下一个公式,用过渡句 ("再考虑…,有:"),不打断三段式节奏。
M3 约束块固定句式
约束条件小节内,每条约束一个段落块:
\textbf{约束n:名称}
一句引入(交代业务/物理动机)。
\[ 公式 \]
其中,…(符号解释;若有近似或线性化,在此追加一句理由)。
- 约束编号 n 全章连续(约束1、约束2…),与公式编号独立计数;
- 名称 4–8 字名词短语,不加句号;
- 使用了 sgn、取整等非光滑近似的约束,理由必须写在"其中"段, 禁止只放脚注。
M4 集合划分列表
凡"将某集合划分",固定两步:
- 总起句:"为了更好地描述约束条件,本文对××集合进行了更细致的 划分。将××集合划分为 n 类如下:"
- 编号列表,每行:
1. D = {i|i = 1, 2, …, m} 表示××的××;- 花括号+竖线条件式枚举;
- 行末分号,末行句号;
- 划分须完备且互斥;材料未说明完备性时停下来向用户确认, 禁止自行补齐。
M5 模型汇总大括号
"模型汇总"小节固定结构:
- 引导句:"本文建立了以××为目标的××优化模型如下:"
- 单个公式环境内用
\left\{\begin{array}{l} … \end{array}\right.实现巨型左大括号(禁止用cases,其强制 text style); 多行等式对齐用嵌套aligned; - 括号内部自上而下:
- 首行:目标函数(max/min W = …);
- 之后:
s.t.对齐后逐行列全部约束(引用前文公式,不重新 推导),每行一个约束,并列条件用\quad分隔; - 末尾若干行:集中列出本问题全部集合定义(与 M4 内容一致, 逐行排版);
- 整个大括号块只占一个公式编号,内部各行禁止单独编号;
- 约束过多超页宽时允许拆成上下两个大括号块,两块合计仍只占 一个编号;禁止缩小字号硬塞。
M6 公式编号与交叉引用
- 编号全文连续,不按节重置;
- 正文引用一律
\eqref{eq:xxx},禁止手写编号数字; - 汇总大括号的编号即该问题模型的总编号,摘要与结果分析引用 模型时统一引用该编号。
硬性禁令
- 禁止修改任何数值、参数、口径——发现疑似问题停下报告,不许"顺手修正";
- 禁止把"其中"符号说明改成三线表或列表;
- 禁止约束编号与公式编号混用同一计数器;
- 禁止在大括号内重新解释符号(解释只出现在前文对应公式处);
- 每写完一节自检:M2 三段式是否完整、M6 编号是否连续,不合格不进入下一节。
三个使用提醒
与数字校验流程解耦:这个 skill 只管“装订”。加载它之后不要再让同一个会话改数字、核口径——一次一个 skill、一个任务,否则它会分心,你之前的权威数字表也多一分被误动的风险。
M5 是技术难点:skill 里已强制 \left{\begin{array}{l} 写法并禁用 cases;若实测某行约束太长溢出页宽,让它改用 optidef 宏包,而不是缩字号。
M4 的完备性检查是它唯一被允许“停下来问你”的地方——如果它没问就默认集合划分没问题,值得在收到交付时反问一句“四个子集的并集是否覆盖全部 54 块地”,防它沉默跳过。
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.
- today First seen · 86 lines · 65 tokens per session scan A 7d31a0438842
mcm-model-typeset is a skill published in the GitHub repository LiXiang106991/MathModelAgent (23 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,479 once invoked, about $0.0003 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 2026-09-20.
Other skills, from other repositories
cumcm-live-workflow
A complete workflow guide for solving China Undergraduate Mathematical Contest in Modeling problems, from checking the computer environment through submitting the final paper.
mathmodel-skill
An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.
cumcm-modeling-analyst
A Chinese-language assistant for CUMCM and similar mathematical modelling competitions, where teams use data and mathematics to solve real-world problems.
review
Write domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry, biology, medicine, mathematics, computerscience, earthenvironment, astronomy, economics, materials) with per-domain style guides mined from landmark reviews in RMP / Nat. Rev. X / Annu. Rev. /…
matplotlib-figures
Publication-quality data plots via matplotlib with venue-specific styles. Use for generating your own figures (timelines, comparison charts, data summaries, heatmaps) that you add to the LaTeX report. Your brain prompt supplies the venue-specific style directory as {{VENUESPECIFICDIR}} — use that value wherever this…
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…