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 XiaoMaColtAI/math-modeling-skill --skill math-modelinggit clone --depth 1 https://github.com/XiaoMaColtAI/math-modeling-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/xiaomacoltai/math-modeling-skill/math-modeling)<a href="https://agentmods.dev/skills/xiaomacoltai/math-modeling-skill/math-modeling"><img src="https://agentmods.dev/badge/skills/xiaomacoltai/math-modeling-skill/math-modeling/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/xiaomacoltai/math-modeling-skill/math-modeling"><img src="https://agentmods.dev/badge/skills/xiaomacoltai/math-modeling-skill/math-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00083 | $0.02961 |
| Opus 5.5 | $0.00033 | $0.01184 |
| Sonnet 5.5 | $0.00017 | $0.00592 |
| Haiku 4.5 | $0.00008 | $0.00296 |
Grade A, and why
math-modeling 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
46 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.
- assets/01-优化算法说明.md 79 KB
- assets/02-预测类算法说明.md 67 KB
- assets/03-评价类算法说明.md 82 KB
- assets/04-图论与网络分析算法说明.md 39 KB
- assets/05-统计分析与数据处理算法说明.md 61 KB
- assets/06-综合类算法说明.md 36 KB
- assets/07-机器学习算法说明.md 52 KB
- assets/README.md 9.1 KB
- references/README.md 2.1 KB
- references/roles/建模手/references/前置合同.md 947 B
- references/roles/建模手/references/工作流程.md 4.2 KB
- references/roles/建模手/references/常见模式.md 5.9 KB
- references/roles/建模手/references/建模设计理论.md 5.5 KB
- references/roles/建模手/references/质检清单.md 1.0 KB
- references/roles/建模手/SKILL.md 2.7 KB
- references/roles/编程手/references/MATLAB规范.md 3.4 KB
- references/roles/编程手/references/工作流程.md 9.9 KB
- references/roles/编程手/references/质检清单.md 4.2 KB
- references/roles/编程手/scripts/apply_publication_style.m 2.2 KB
- references/roles/编程手/scripts/audit_publication_figure.m 3.4 KB
- references/roles/编程手/scripts/check_env.py 2.7 KB runs code
- references/roles/编程手/scripts/check_matlab_env.m 1.3 KB
- references/roles/编程手/scripts/export_publication_figure.m 1.4 KB
- references/roles/编程手/scripts/figure_audit.py 7.1 KB runs code
- references/roles/编程手/scripts/plot_style.py 17 KB runs code
- references/roles/编程手/scripts/repro_manifest.py 4.2 KB runs code
- references/roles/编程手/SKILL.md 6.3 KB
- references/roles/论文手/references/LaTeX格式规范.md 3.9 KB
- references/roles/论文手/references/写作规范.md 4.5 KB
- references/roles/论文手/references/工作流程.md 11 KB
- references/roles/论文手/references/自审框架.md 5.0 KB
- references/roles/论文手/references/英文化工作流.md 5.2 KB
- references/roles/论文手/references/论文格式规范.md 4.7 KB
- references/roles/论文手/references/论文模板.docx 15 KB
- references/roles/论文手/references/章节模板.md 1.7 KB
- references/roles/论文手/SKILL.md 11 KB
- references/Subagent调度.md 7.4 KB
- references/交付与截止时间协议.md 4.4 KB
- references/算法索引.md 1021 B
- tools/docx/SKILL.md 6.6 KB
- tools/figure/SKILL.md 13 KB
- tools/latex/SKILL.md 8.7 KB
- tools/paper_search/SKILL.md 1.9 KB
- tools/pdf/SKILL.md 7.9 KB
- tools/xlsx/SKILL.md 2.3 KB
- 使用指南.md 3.4 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 · +1 lines 3cbb7985e91d
- 1mo ago Changed · +2 lines 64d8a2dd049c
- 1mo ago First seen · 137 lines · 83 tokens per session scan A fe5236cfa0f7
math-modeling is a skill published in the GitHub repository XiaoMaColtAI/math-modeling-skill (1,874 stars, last pushed yesterday), with no licence file. It adds 83 tokens to every session and 2,961 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
math-research-activator
A routing guide for mathematical analysis in AI research and cryptography. It helps an agent choose the relevant mathematical ideas and checks for a problem.
fitness-exercises-get-exercises
Returns a paginated list of exercises. All filter parameters are optional and combinable.
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-{id}
Returns a single exercise by its numeric ID.
math-research-activator
A routing guide for mathematical work in AI and cryptography. It helps choose the right concepts and checks for architecture design, theory, mathematical transfers, definitions, constructions, proofs of security, and protocol reviews.
literature-searcher
Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.