math-model-code

math-model-code is a skill for Claude Code, Codex from OrinVoss/dsh-math-team. It costs 98 tokens per session (6,664 once invoked), scanned A, original, MIT.

A team workflow for solving mathematical modelling problems with code, including analysis, model selection, computation, plots, and reproducibility notes.

In plain words
What is it for?
Use it to build and test mathematical models, run calculations, create figures, and submit only your assigned folder.
Why use it?
It defines where each team member works and prevents members from overwriting one another’s files while collaborating through Gitee, a Git-based code hosting service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to build and test mathematical models, run calculations, create figures, and submit only your assigned folder.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orinvoss/dsh-math-team/math-model-code
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.

Any agent
npx skills add OrinVoss/dsh-math-team --skill math-model-code
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-model-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/math-model-code/github.svg)](https://agentmods.dev/skills/orinvoss/dsh-math-team/math-model-code)
Your own site
<a href="https://agentmods.dev/skills/orinvoss/dsh-math-team/math-model-code"><img src="https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/math-model-code/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.

agentmods 80×15 button for math-model-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/orinvoss/dsh-math-team/math-model-code"><img src="https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/math-model-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,664 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.06664
Opus 5.5 $0.00039 $0.02666
Sonnet 5.5 $0.00020 $0.01333
Haiku 4.5 $0.00010 $0.00666

Measured 1mo ago against content hash e6b452ead47d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

math-model-code 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/read_pdf.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/model-code/skills/math-model-code/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

建模 + 编程岗(团队数学建模)

你是团队中负责「建模 + 编程」的 agent,与另一名同岗成员各自在独立会话/工作区工作,互不干扰。你们通过同一个 Gitee 仓库的三个独立子文件夹协同:member-a/、member-b/(建模+编程,各占其一)、member-c/(论文岗)。本 skill 约定你的职责、交付物与门禁。

团队协同模型(强制)

  • 你的工作区 = 你的独立 DSH 会话工作目录下、Gitee 仓库的 member-你的 文件夹(你是 member-a/ 或 member-b/)。
  • git clone 同一仓库后,只读写你所属的 member-* 文件夹;git add 必须限定在自身文件夹内,绝不 git add . 越过自身目录,绝不修改 member-a/、member-b/、member-c/ 之外或他人的文件。
  • git pull 可拉取他人最新交付(A、B 建模结果、评审反馈),但只读、不覆盖改写。
  • 产物只写在你自身的 member-* 目录下,达到门禁后再 git add <自身目录> && git commit && git push。

初始建库(仓库尚为空时,首个成员执行)

# 在 gitee 建好空私有仓库后,本机(若 Gitee 走代理/报 schannel 错,先执行两条 config)
git config http.sslBackend openssl
git config http.proxy http://127.0.0.1:10808    # 仅当需要代理

# 建三个独立文件夹并推送基线(在仓库根执行一次)
mkdir -p member-a member-b member-c
printf '建模编程成员 A 工作区\n' > member-a/README.md
printf '建模编程成员 B 工作区\n' > member-b/README.md
printf '论文岗成员 C 工作区\n'   > member-c/README.md
git add member-a member-b member-c
git commit -m "init: 团队三文件夹基线"
git branch -M main && git push -u origin main

普通成员后续 clone / 更新

git clone <gitee-repo-url>          # 之后在此仓库根下的自身 member-* 内工作
git pull                            # 开始时拉取最新;只读他人文件夹

我的职责(两阶段)

阶段一:建模分析

先完整理解题目与附件,再形成结论与模型方案:

  1. 读题与盘点:完整读题,检查附件(data/),确认目标、约束、评价口径;列清全部子问题。 PDF 题目/附件用「双通道读取 + 对齐」(强制,防漏读):
    • 一条命令产出两个通道(脚本随本 skill 提供): uv run --with pypdf --with pymupdf python <SKILL_ROOT>/scripts/read_pdf.py <题目.pdf> <PROJECT_ROOT>/题目提取 150 → 生成 <PROJECT_ROOT>/题目提取/<题目>.txt(文本)与 page_NN.png(每页渲染图,150 DPI)
    • 文本通道:用 read 读 .txt——便于检索、复制、逐字核对数字与措辞;
    • 图像通道:用 read_image 逐页看 page_NN.png——保留公式、表格结构、上下标、图片与版式原貌(这些正是文本提取最容易丢失或错乱的部分);
    • 对齐核对(强制):两个通道交叉核对数字、公式、单位、附件编号;发现不一致或明显缺漏时以图像通道为准,并在 题目分析报告.md 里记录差异(例如"附件 N 的公式在文本提取中丢失,已按第 X 页图像补全")。
    • 页数很多时,至少完整渲染并查看含题目要求、数据说明、附件定义的关键页。
  2. 输出固定交付物(写到 member 文件夹):
    • 题目分析报告.md:子问题拆解、每个子问题的目标/约束/数据、计划采用的方法。
    • 术语表格.md:符号、单位、关键定义统一表。
  3. 建模约束:
    • 每个子问题最多使用两个独立模型体系。物理题中同一控制方程的近似/展开计为一个模型族,不机械拆分成多个。
    • 创新必须来自问题结构、数据处理、约束设计、算法改进或验证方式,并说明依据;禁止堆砌常见简单模型冒充创新。
    • 数据判定标准按题目、官方规则、领域文献或数据分析结果确定;不因两模型结果相近就强制删其一。

Read the full file on GitHub · 214 lines

Files

What ships with it

32 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · +55 lines e6b452ead47d
  2. 2mo ago First seen · 159 lines · 98 tokens per session scan A ff3ef5a53cbd

Subscribe to this mod's changes

math-model-code is a skill published in the GitHub repository OrinVoss/dsh-math-team (7 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 6,664 once invoked, about $0.0004 per session on Opus 5.5. 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

math-model-code compared with skills from other repositories

math-model-code next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
math-model-codeOrinVoss/dsh-math-teamSkill71mo agoMITA98Claude Code, Codex
deep-learning-pytorchMindrally/skillsSkill29729d agoApache-2.0A33Claude Code
nlp-natural-language-processingMindrally/skillsSkill29729d agoApache-2.0A28Claude Code
jax-best-practicesMindrally/skillsSkill29729d agoApache-2.0A18Claude Code
bio-workbenchpoplarity/dsh-science-workbenchSkill118d agoMITA147Claude Code, Codex
huggingface-transformersalivirgo/Major-AI-SkillsSkill2yesterdayMITA28Claude Code
write-cuda-layernorm-kerneltensormux/kernel-skillsSkill894mo agoMITA0Claude Code, Codex