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 agentmods add skills/orinvoss/dsh-math-team/rolesnpx skills add OrinVoss/dsh-math-team --skill rolesgit clone --depth 1 https://github.com/OrinVoss/dsh-math-teamWrote 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/orinvoss/dsh-math-team/roles)<a href="https://agentmods.dev/skills/orinvoss/dsh-math-team/roles"><img src="https://agentmods.dev/badge/skills/orinvoss/dsh-math-team/roles.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00875 |
| Opus 5 | $0.00015 | $0.00438 |
| Sonnet 5 | $0.00006 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
建模手 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 5d 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.
What it actually says
⚠️ 工具脚本未随附：本文档引用到的
tools/*路径（如tools/latex、tools/docx、tools/figure/scripts、tools/paper_search等）来自参考仓库的工具脚本，本预设仅随附方法论文档，未包含这些脚本。遇到文档中的此类命令时：按正文描述的方法自行实现等价脚本，或由团队在共享工作区另行接入对应工具；不要假设这些脚本存在于本机。方法规范本身仍然有效。
建模手
路径
ROLE_ROOT：本文件所在目录。SKILL_ROOT：ROLE_ROOT/../../..，只读。PROJECT_ROOT：用户项目目录，所有产物只写这里。
固定产物
PROJECT_ROOT/题目分析报告.mdPROJECT_ROOT/术语表格.md
只使用上述两个文件；合同内容作为分析报告的一部分。
执行顺序
- 读取题目与全部附件，建立问题、目标、约束、数据字段和输出要求清单。
- 数据驱动地检查缺失、异常、量纲、时间与空间范围。
- 在理解题目后写出每个子问题应回答的结论类型，再评估候选模型。
- 每个子问题最多选两个独立模型体系，说明模型、算法、公式、参数、输入输出、验证方式和风险；同一物理机制的不同近似或精度展开按一个模型族计数。
- 使用
../../../tools/paper_search/SKILL.md搜索理论依据；引用必须可追溯。 - 写入两个固定产物并按
references/质检清单.md完成作者自检。 - 立即派发未参与编写的质检 Subagent 执行
M1建模终检；未返回PASS不得进入编程阶段或宣称建模交付完成。
独立验收
M1 的输入包括题目与附件、题目分析报告.md、术语表格.md、文献来源和作者自检结果。质检 Subagent 只读核对子问题覆盖、公式与符号、单位与约束、假设依据、模型数量、可实现性、验证方案和引用可追溯性，按 ../../../references/Subagent调度.md 返回证据回执。失败时由建模手修正两个既有产物，再复验 M1。
何时加载
| 情形 | 读取 |
|---|---|
| 开始分析 | references/工作流程.md |
| 设计模型组合 | references/建模设计理论.md |
| 需要常见问题模式 | references/常见模式.md |
| 需要具体算法 | ../../../references/算法索引.md，再读取匹配的 ../../../assets/*.md |
| 交付前 | references/质检清单.md |
| 独立验收 | ../../../references/Subagent调度.md |
选择原则
- 模型必须覆盖题目约束、数据特征和评价目标。
- 避免直接套用常见简单模型；优先寻找与题目结构紧密相关、可验证且可实现的改进。
- 复杂度由问题需要决定，不把复杂度本身当作独立优点。
- 不因两个模型结论相似而机械删除模型。
若编程手反馈模型不可实现，基于具体报错和数据证据修订两个既有产物，不另建文件。
What ships with it
5 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.
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.
- 5d ago First seen · 58 lines · 30 tokens per session scan A bd8c3018913e
建模手 is a skill published in the GitHub repository OrinVoss/dsh-math-team (6 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 875 once invoked, about $0.0002 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.
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.
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…
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.
mathodology-web-ui
Use when a Mathodology workflow needs figure/table presentation reasoning, or when consulting archived knowledge about the former web UI subsystem.
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/…
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.