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/the-thinker0/math-skill/math-skillnpx skills add the-thinker0/math-skill --skill math-skillgit clone --depth 1 https://github.com/the-thinker0/math-skillWhat 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 | $0.00151 | $0.02588 |
| Opus 5 | $0.00076 | $0.01294 |
| Sonnet 5 | $0.00030 | $0.00518 |
| Haiku 4.5 | $0.00015 | $0.00259 |
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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数学研究路由器
本文件是权威入口（Claude Code / Codex / Cursor / DeepSeek Harness 等均加载此文件）。按用户主语言回答；技术词、代码、路径和公式不决定语言。SKILL.en.md 只供 /ask 英文入口等显式英文兼容路径加载，两者不同时加载——在本文档内即可中英作答。
目标与硬约束
把问题路由到最少但足够的数学材料，并给出可证伪、带条件的结论。
- 区分定理、建模假设、经验规律和探索性猜想；不得把后两者写成保证。
- 数学锚点先讲数学结构；AI 设计模式和密码学安全语义分域加载。
- 不因目录中存在材料而整目录加载。书稿只用于卡片不足、需核对定理条件或用户要求出处时。
- 必须收敛到结论；不要只列视角、术语或加载清单。
何时介入
先看用户要求的目标与保证，不要按单个关键词投票。
- 若任务只要求修 import/shape/OOM、重构、改配置、调参、部署或一般代码质量审查，归为 E 纯工程，不介入。
- 若任务虽含代码，但要求验证数学正确性、复杂度、收敛性、数值稳定性或密码学安全性，仍应介入。
- 用户直接要求设计、分析、验证或解释相关数学时，任务信号本身足够；工作区文件只用于消歧，不是必需门槛。
/ask、/math-research-activator或显式点名本 skill 时，跳过自动触发判断，但仍排除与数学/安全语义无关的纯工程工作。
| 场景 | 用户目标 | 最小路径 |
|---|---|---|
| A 分析 | 判断设计、假设或论证是否合理 | 1–2 透镜 → 条件/反例审查 |
| B 设计 | 构造新机制、算子、loss、路由或协议 | 1–2 透镜 → 1–3 锚点 → 0–2 设计原型 → 审查 |
| C 查询 | 理解与研究问题相关的数学概念 | 通常 1 张锚点 |
| D 验证 | 判断公式、保证、归约或复杂度声称是否成立 | 1–2 锚点 → 条件/边界/反例 |
| E 工程 | 仅实现与维护 | 不加载本系统材料 |
Domain Router
按目标对象和所需保证判域：
| 域 | 加载范围 | 禁止污染 |
|---|---|---|
| 共用数学 | lenses/ + knowledge-base/ 中除 knowledge-base/cryptography/ 外的 8 域 37 锚点 |
不自动加载 AI 模式或密码书稿 |
| AI 研究 | 共用数学按需 + design-patterns/ 中相关的 0–2 个原型 |
不加载密码学锚点/书稿 |
| 密码学 | knowledge-base/cryptography/ 中相关锚点；不足时再查 3 本密码书稿；共用数学按结构按需 |
不加载 AI 设计模式，不以 GPU 清单作安全门 |
| AI×密码 | 同时满足“密码学原语/形式安全性质”和“AI 对象/功能需求”，且问题要求迁移或组合 | 只加载交叉点实际需要的两侧材料 |
判定细则：
hashing、attack、security等表面词不足以判密码域。特征哈希通常是 AI；对抗样本只有在要求攻击游戏、证书或归约时才进入密码/交叉域。- 纯密码问题使用安全定义、归约紧度、假设依赖和实现陷阱检查；GPU 只在用户明确问密码实现性能时作为普通工程分析，不作为安全验收门。
- 交叉问题输出一次四元组：①原语+安全性质；②AI 对象+功能需求；③迁移方向；④迁移后假设是否仍可满足。非交叉问题不要输出该模板。
完整索引与语言边界例见 references/skill-index.md；不要为了路由而默认读取它。
渐进加载与 token 预算
默认遵循下列上限；只有用户要求全面审查、多个候选或原材料确实不足时才扩展。
| 场景 | 默认加载预算 | 默认回答预算 |
|---|---|---|
| A | 1–2 透镜；必要时 1 锚点 | 结论 + 2–4 个关键问题 + 修法 |
| B | 1–2 透镜、1–3 锚点、0–2 模式 | 1 个主方案；备选只写关键差异 |
| C | 1 锚点 | 定义 + 公式/直觉 + 适用边界 |
| D | 1–2 锚点 | 短结论 + 成立条件 + 不能保证什么 |
- 不复述卡片全文，不展示内部加载路径，除非用户在调试路由、问题跨域或存在歧义。
- 简单问题不套完整报告模板；每个标题必须承载新信息。
- 用户只问概念时，不主动展开 AI 翻译、GPU 评分或长参考书目。
- 若一个锚点已足够，不再加载同主题书稿。若卡片和自身可靠知识足够，不进入 PDF。
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.
- 2d 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 (10 stars, last pushed 6d ago), licensed MIT. It adds 151 tokens to every session and 2,588 once invoked, about $0.0008 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
math-skill
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling.
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.
design
Writes a clear design for a proposed feature or system change. Use when important product or technical choices must be settled before coding. Covers behavior, interfaces, failures, risks, acceptance criteria, and tests. Use architecture when the repository needs current ARCHITECTURE.md.
architecture
Creates or updates root ARCHITECTURE.md from verified implementation. Use when a repository needs current architecture documentation or a structural change made it stale. Use design for proposed systems or changes.
html-doc
Generates a polished, static HTML reading view from an existing Markdown PRD or technical design. Use when a user asks to render, present, visualize, or make a PRD or design document easier for humans to read in a browser.
plan
Turns an approved design or decided brief into ordered tasks for separate agent runs. Use for implementation tasks, tracker tickets, or useful milestones. Do not use for one coding task or its short execution outline.