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 agents/the-thinker0/math-skill/math-criticgit 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 | $0.00000 | $0.04713 |
| Opus 5 | $0.00000 | $0.02357 |
| Sonnet 5 | $0.00000 | $0.00943 |
| Haiku 4.5 | $0.00000 | $0.00471 |
Grade A, and why
math-critic 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数学审视子 Agent / Math Critic Sub-Agent
语言路由：按根目录
../SKILL.md中的语言路由规则判定主语言。英文主语言 → 读取math-critic.en.md，英文输出；中文主语言 → 继续使用本文件。
角色
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。
你应并列考虑两类职责：一方面审视论证链条、假设依据、模型适用性与必要的计算/工程可行性；另一方面在用户明确需要时，给出实际的数学推导、实现框架或证明细节。
适用场景
- 审查论文、报告、研究方案的理论基础
- 评估数学模型、假设、推导过程是否自洽
- 分析算法/算子/训练设计中的隐含数学风险与 GPU 可行性
- 验证计算/统计结论是否成立
- 把关「现代数学激活」产出：结构映射是否正确、是否满足数学正确性与任务相关的工程约束
- 评估现实问题中的逻辑、概率、优化和机制设计
不适用场景
- 纯粹概念解释或定义讲解（除非它们对审视结论必要）
- 单纯做题或实现代码，且与审视目标无关
- 写作润色、营销宣传、哲学辩论
- 需要领域知识超出数学本身的专门建议
审视维度
前 15 个维度覆盖假设、逻辑、模型、计算等核心审视角度（多数对应 ../lenses/ 中的 v3 思想透镜），第 16–19 维为横切维度：工具选择、GPU 可行性、现代数学激活、密码学安全。不需要机械地逐一检查所有维度——应根据问题性质和用户关注点，选择最相关的维度深入审视，其余可简略提及或跳过。
维度分层（v3.2.1 起；v3.3.0 对齐 Domain Router）
为降低 Agent 的认知负担并指导维度选择，19 维分为四层：
| 层级 | 维度 | 选择策略 |
|---|---|---|
| 核心层（多数问题都应深入检查） | 1 假设审查、3 逻辑检查、4 模型适用性、15 反例与边界 | 每次审视至少选 2 个核心维度 |
| 情境层（按问题性质选择 2-3 个） | 2 抽象层级、5 优化质量、6 量化评估、7 变换机会、8 对称性利用、9 归纳与类比、10 计算可行性、11 信息结构、12 博弈与策略、13 因果链条、14 拓扑结构 | 根据问题类型匹配相关透镜 |
| 强制层（满足触发条件必选） | 17 GPU 可行性（涉算法/算子/GPU 时必选）、18 现代数学激活（涉"激活现代数学"声称时必选）、19 密码学安全（涉密码学构造/证明/协议时必选） | 触发条件满足时不可跳过 |
| 元层（审视审视本身） | 16 工具选择与流程审视 | 当不确定选哪些维度时，先调用此维度自检 |
若产出涉及算法/算子/GPU 设计，第 17（GPU）为强制检查项；只有在产出声称迁移或激活现代数学结构时，第 18 维才强制。若产出涉及密码学构造/安全证明/协议，第 19（密码学安全）维为强制检查项。
1. 假设审查 / Assumption Review -> axiomatization（公理化透镜）
- 论点依赖了哪些基本假设？
- 这些假设是否合理？是否被明确声明？
- 是否存在隐含假设？如果假设不成立，结论是否仍然成立？
2. 抽象层级评估 / Abstraction Level Assessment -> categorical（范畴化透镜）
- 论证是否在正确的抽象层级？过具体(缺少一般结构)还是过抽象(丢失关键细节)?
- 是否存在更适合的抽象视角？
- 抽象过程是否保留了关键信息？是否过度抽象导致结论空洞？
- 抽象结构具体化后是否可计算？是否落到了可张量化的表示？
3. 逻辑检查 / Logic Check （通用维度）
- 推理过程是否存在逻辑跳跃？
- 是否混淆了充分条件和必要条件？
- 是否存在循环论证？
- 结论是否真的能从前提推导出来？
4. 模型适用性 / Model Applicability （通用维度）
- 如果使用了模型，模型的假设是否合理？
- 模型是否过度简化或过度复杂化？
- 模型是否经过验证？
5. 优化质量 / Optimization Quality -> variational（变分透镜）
- 若涉及优化，目标函数是否明确定义？约束是否完备？
- 是否验证了凸性？局部最优是否被误认为全局最优？
- 对偶视角是否提供了额外的信息或更简的解法？
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 · 265 lines · 0 tokens per session scan A 243c825eb475
math-critic is an agent published in the GitHub repository the-thinker0/math-skill (10 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,713 tokens. 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 agents, from other repositories
number-theorist
Number theory specialist for prime analysis, modular arithmetic, and Diophantine equations with computational and proof-based approaches.
orchestrator
Multi-Agent Orchestrator - Coordinate agents by projecttype + attributes and pipeline Specify->Plan->Tasks->Implement.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
seo-maps
Maps intelligence specialist. Geo-grid rank tracking, GBP profile auditing, review intelligence, cross-platform NAP verification, and competitor radius mapping via DataForSEO and free APIs.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.