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 the-thinker0/math-skill --skill math-skillgit clone --depth 1 https://github.com/the-thinker0/math-skillWrote 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/the-thinker0/math-skill/math-skill)<a href="https://agentmods.dev/skills/the-thinker0/math-skill/math-skill"><img src="https://agentmods.dev/badge/skills/the-thinker0/math-skill/math-skill/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/the-thinker0/math-skill/math-skill"><img src="https://agentmods.dev/badge/skills/the-thinker0/math-skill/math-skill.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 | $0.00163 | $0.02296 |
| Opus 5.5 | $0.00065 | $0.00918 |
| Sonnet 5.5 | $0.00033 | $0.00459 |
| Haiku 4.5 | $0.00016 | $0.00230 |
Grade A, and why
math-research-activator 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数学研究：从问题到构造与验证
本文件是 Claude Code / Codex / Cursor / DeepSeek Harness 的权威入口。按用户自然语言主框架回答；技术词、代码、路径、公式不决定语言。SKILL.en.md 仅供显式英文兼容入口，两份正文不同时加载。所有资源路径相对本 skill 安装目录（dsh 的 resourceBase），不是用户项目根目录。
要完成什么
帮用户解释、推导或构造能解决当前研究问题的机制。数学材料服务于这个任务，不能以选择透镜、列术语、生成知识卡或给模板命名作为交付。
- 用户已有目标、方案与约束时沿用；只有会改变结论的缺口才澄清，能带明确假设继续的就推进。
- 区分已有定理、当前推导、建模假设和经验结果；每个“最优、稳定、安全、等价”都要有相应条件。
- 用户要求实现/验证且环境允许时，执行已授权的最小检查并据观察修改候选。只要求概念或计划时按该范围交付。
先按任务分流
数学正确性、复杂度、收敛、稳定性或密码学安全性是目标时，即使任务含代码也介入。仅修 import/shape/OOM、重构、调参、部署或一般代码质量属于 E 纯工程，不加载研究材料。直接点名本 skill 可跳过自动触发判断，仍尊重纯工程边界。
| 场景 | 需要交付 | 材料怎么用 |
|---|---|---|
| A 分析 | 当前论点是否成立、关键原因与修法 | 从已有对象出发；相关锚点或透镜，不先做全套诊断 |
| B 跨域探索 | 找到有价值、结构上不同的数学思路 | 先读 结构迁移，不以现有原型限定候选 |
| B 构造 | 将选定思路导出机制，说明实现与验证 | 需要落实数学化与实现时，读 构造工作台 |
| C 查询 | 定义、直觉、公式与适用边界 | 通常一张锚点；不追加设计/GPU/实验报告 |
| D 验证 | 推导、条件界或最小反例 | 通常 1–2 锚点；用户要求运行时完成检查 |
| E 工程 | 按工程任务处理 | 不加载本系统材料 |
用户希望跨数学领域启发或减少模板化时，先去掉应用名字，寻找当前方案未满足的结构关系。沿不同数学表述发现候选，展示准确对象对应与能迁回的结论；不可能性和信息不足也是有效研究见解。生成阶段先不读设计原型，待关键映射成立后再查作对照。数学构造动作中的五例同样不是候选清单边界。
B 构造场景再确定希望改变的行为与决策时可用的信息，选择数学对象。构造工作台提供从对象到算子、落实定理假设、通过小验证取舍的动作。数学构造动作 按相关一节选读，可产生现有 22 个设计原型以外的机制；已有原型只作参照。
Domain Router
按目标对象与所求保证判域，不能只数关键词。
| 域 | 可用材料 | 边界 |
|---|---|---|
| 共用数学 | lenses/ 与 8 个非密码域的 37 张锚点 |
不自动加载 AI 原型或密码书稿 |
| AI 研究 | 共用数学、构造工作台、相关 AI 原型 | 不加载密码学锚点/书稿 |
| 密码学 | knowledge-base/cryptography/ 的相关锚点；共用数学按结构需要补充 |
不加载 AI 原型/构造动作，不以 GPU 清单判断安全 |
| AI×密码 | 同时涉及密码学原语/形式安全性质与 AI 对象，且要求迁移或组合 | 只读交叉点所需材料 |
hashing、attack、certificate、一般证明或对抗优化不足以判密码域；特征哈希、Lipschitz 鲁棒性证书、随机平滑认证通常仍是 AI。统计隐私定义本身也不等于密码学。
交叉问题说明一次：原语及安全性质、AI 对象及功能、迁移方向、迁移后的假设是否可满足。纯密码任务先写攻击者能力、安全游戏、优势和归约资源；实现注意事项按具体方案选择。只有用户问密码实现性能时才分析相关硬件成本。
只读会改变当前决定的材料
- 已知所需数学结构时直接读锚点，不必先过透镜或索引。概念/短验证一般只需 1–2 份材料；构造任务可从工作台加 1–3 份相关资源起步，推导与验证确有需要再扩展。
- 透镜用于发现形式化方式，不是每次必走步骤；文件名不足以定位时才读 索引。已有上下文足够时不重复读取。
- 锚点先读定义、核心公式及影响结论的风险/条件；设计原型已重复的数学段可以跳过。文件短或工具不支持分节时可读单文件。
- 卡片不足、需核对精确条件或用户要求来源时才读书稿/原论文。构造工作台、完整 critic 与 GPU 清单都不是所有任务的常驻上下文。
- 不展示内部文件加载路径或流程标签，除非用户在调试 skill；不复述材料，不把简单问题写成全面审查。
What ships with it
44 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.
- references/agentic-workflow.en.md 3.8 KB
- references/agentic-workflow.md 3.1 KB
- references/books/abstract-algebra.en.md 17 KB
- references/books/abstract-algebra.md 14 KB
- references/books/algebraic-geometry-rising-sea.en.md 4.4 KB
- references/books/algebraic-geometry-rising-sea.md 3.9 KB
- references/books/applied-cryptography.en.md 3.1 KB
- references/books/applied-cryptography.md 2.9 KB
- references/books/differential-geometry.en.md 13 KB
- references/books/differential-geometry.md 10 KB
- references/books/foundations-of-cryptography.en.md 2.8 KB
- references/books/foundations-of-cryptography.md 2.5 KB
- references/books/introduction-to-modern-cryptography.en.md 3.1 KB
- references/books/introduction-to-modern-cryptography.md 2.8 KB
- references/books/matrix-analysis.en.md 17 KB
- references/books/matrix-analysis.md 14 KB
- references/books/micro-lie-theory.en.md 10 KB
- references/books/micro-lie-theory.md 9.5 KB
- references/books/optimization-ml.en.md 14 KB
- references/books/optimization-ml.md 11 KB
- references/books/smooth-manifolds.en.md 13 KB
- references/books/smooth-manifolds.md 11 KB
- references/construction-moves.en.md 12 KB
- references/construction-moves.md 9.0 KB
- references/design-workbench.en.md 8.3 KB
- references/design-workbench.md 6.0 KB
- references/gpu-friendly-math.en.md 9.1 KB
- references/gpu-friendly-math.md 7.8 KB
- references/inspiration.en.md 3.6 KB
- references/inspiration.md 2.9 KB
- references/musings.en.md 4.5 KB
- references/musings.md 3.9 KB
- references/skill-index.en.md 15 KB
- references/skill-index.md 12 KB
- references/structural-transfer.en.md 8.1 KB
- references/structural-transfer.md 5.9 KB
- references/transfer-bridges.en.md 4.4 KB
- references/transfer-bridges.md 3.4 KB
- references/worked-examples/equivariance-check.en.md 3.7 KB
- references/worked-examples/equivariance-check.md 3.5 KB
- references/worked-examples/query-aware-compression.en.md 3.7 KB
- references/worked-examples/query-aware-compression.md 3.5 KB
- references/worked-examples/security-reduction.en.md 3.6 KB
- references/worked-examples/security-reduction.md 3.3 KB
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.
- 1mo ago Changed · -51 lines · +12 tokens per session 490a501cc5c6
- 1mo ago First seen · 134 lines · 151 tokens per session scan A e0df229071b5
math-research-activator is a skill published in the GitHub repository the-thinker0/math-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 2,296 once invoked, about $0.0007 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.
Other skills, from other repositories
科研可视化工具
A research-visualisation workflow for examining data and producing publication-ready charts for scientific papers.
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
fitness-exercises-post-batch
Fetches up to 50 exercises by their numeric IDs in a single request. IDs that do not exist are silently skipped. Results are returned in the same order as the input array.
fitness-exercises-get-exercises
Returns a paginated list of exercises. All filter parameters are optional and combinable.