math-modeling-solver

math-modeling-solver is a skill for Codex from mantou6666/Math-Modeling-Agent-Flow. It costs 138 tokens per session (6,947 once invoked), scanned A, original, MIT.

A workflow for solving mathematical modelling competition problems and certifying the results. It covers understanding the problem, choosing models and algorithms, running searches, checking the evaluator, and documenting reproducible results.

In plain words
What is it for?
Use it to define a problem contract, explore and improve mathematical models, audit optimization searches, validate feasibility and numerical results, and produce a result certificate.
Why use it?
It reduces the risk of solving the wrong formal problem, using an incorrect scoring method, missing better solutions, or claiming more certainty than the checks support.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Install

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.

agentmods
npx agentmods add skills/mantou6666/math-modeling-agent-flow/math-modeling-solver
Any agent
npx skills add mantou6666/Math-Modeling-Agent-Flow --skill math-modeling-solver
Clone the repo
git clone --depth 1 https://github.com/mantou6666/Math-Modeling-Agent-Flow

Made for: Codex.

Wrote 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.

agentmods badge for math-modeling-solver

README.md
[![agentmods](https://agentmods.dev/badge/skills/mantou6666/math-modeling-agent-flow/math-modeling-solver.svg)](https://agentmods.dev/skills/mantou6666/math-modeling-agent-flow/math-modeling-solver)
Your own site
<a href="https://agentmods.dev/skills/mantou6666/math-modeling-agent-flow/math-modeling-solver"><img src="https://agentmods.dev/badge/skills/mantou6666/math-modeling-agent-flow/math-modeling-solver.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00138 $0.06947
Opus 5 $0.00069 $0.03474
Sonnet 5 $0.00028 $0.01389
Haiku 4.5 $0.00014 $0.00695

Measured 6d ago against content hash 12be6403ff12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

math-modeling-solver 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 6d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (references/implementation-starters/python/decision/multicriteria_starter.py, references/implementation-starters/python/learning/tabular_baseline_starter.py, references/implementation-starters/python/learning/time_series_backtest_starter.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

math-modeling-solver/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Math Modeling Solver — Public Research Workflow 3.1.0-rc2

本 Skill 的唯一目标是把赛题从题面推进到可被论文安全引用、可回查、可复现的认证结果。方法参考、场景模式、论文和公开代码只提供候选结构与证据,不拥有题意、formal evaluator、正式结果或回退权。

默认采用“整题理解、逐问高质量闭环”。完成一问后允许切换新对话,只读取 PROJECT_CONTEXT.md、本问材料和直接依赖的 Result Certificate;不得为了在一个上下文里赶完全部问题而压缩后续推理、研究或验证。

0. 权威边界与工作意图

Solver 唯一拥有:题意规格、Problem Contract、模型定义、变量、目标、约束、formal evaluator、搜索空间、正式运行、正式结果、optimality_status 与 Result Certificate。

不拥有:论文最终措辞、参考文献编号、DOCX 版式、最终支撑材料打包。

复杂任务可在 work order 或当前任务头部设置轻量 operation_intent

  • DISCOVER:寻找不同模型、表示、结构、搜索区域和盲区;允许研究和 exploratory runs,不签发正式结果。
  • IMPROVE:Problem Contract 与 formal evaluator 已冻结,只优化候选生成、搜索策略、参数与精修;发现 contract/evaluator 有错时退出本意图并进入 Repair。
  • CERTIFY:停止追高,只检查题意一致性、feasibility、formal evaluator、数值精度、稳定性、复现与最优性措辞;不得自动开启新算法、benchmark 或大规模正式搜索。

Repair Mode 单独保留,不并入三种 intent。

0.1 人机协同默认(Human-in-the-loop defaults)

默认把模型/算法选择与正式结果采用视为用户参与的决策,而不是 AI 单方闭环。候选生成、研究、验证、求解的完整能力保持不变,改变的是"谁决定"的默认语义。

  • 用户已有明确思路/方向时:AI 沿用户思路拔高——补强、落地、验证、控制风险,不擅自更换主线;确有必要换路线时先说明理由并获得同意。
  • 用户没有思路时:AI 提供若干真正不同的候选方案,每条附推荐依据(数学适配、可解性、证据成本、剩余风险),由用户选择;用户可显式委托 AI 推荐(AI_DELEGATED),此时 AI 给出单一推荐及理由,其余候选仍可回退。
  • 正式结果认证与采用前,默认有一次用户知情/确认点(路线、主要假设、最优性措辞);用户显式委托全权时可合并。
  • 模型/算法选择决策记录来源标记(写入 work order / checkpoint 文本字段):
    • HUMAN_SELECTED:用户选定;
    • AI_RECOMMENDED:AI 推荐、用户确认;
    • AI_DELEGATED:用户显式委托 AI 决定;
    • HUMAN_REVIEWED:AI 生成、用户复核。
  • 以上不构成固定门禁:简单确定性问题或用户明确要求全权时,可跳过部分确认点;验证深度仍由最大剩余风险驱动。

0.2 Public 默认交互:先拔高,再执行

Public Edition 收到新题或团队方案时,默认先完成 Frame → Expand → Recommend,然后把候选路线、取舍理由和风险交给团队选择或显式委托。DISCOVER/IMPROVE 不得因为 Skill 自己“已经有把握”就无人值守跑完整题。

当用户明确说“继续实现 / 求解 / 运行 / 验证”,或已显式委托 AI 全权推进时,才进入程序执行与 Formal Evaluation Contract;已有可运行结果并要求收口时进入 CERTIFY。这只改变默认自动化程度,不削弱明确授权后的求解、搜索、反证和认证能力。

0.3 Portable Artifact Contract

从 Solver 开始,所有会进入 JSON/Markdown、handoff、certificate、manifest 或最终 ZIP 的文件引用统一相对 PROJECT_ROOT 保存,并使用 POSIX /。绝对路径只允许在运行时内存中解析,不得持久化。跨 Skill 只传 path + sha256 + owner/result_id 的项目相对引用。

正式输入若位于项目目录外,应先导入 inputs/ 或其他明确打包目录;不得把机器固定路径写进 artifact。推荐结构为 inputs/ → artifacts/ → paper/ → final/ → outputs/,这样整个项目目录可以直接压缩、复制、换机器后重新指定 PROJECT_ROOT 继续工作。详见 references/core/portable-artifacts.md

Read the full file on GitHub · 315 lines

Files

What ships with it

60 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.

Changes

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.

  1. 6d ago First seen · 315 lines · 138 tokens per session scan A 12be6403ff12

Subscribe to this mod's changes

math-modeling-solver is a skill published in the GitHub repository mantou6666/Math-Modeling-Agent-Flow (16 stars, last pushed 17d ago), licensed MIT. It adds 138 tokens to every session and 6,947 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

drug-discovery

Drug discovery: ChEMBL search, drug-likeness, interactions.

NousResearch/hermes-agent · 19 tokens

jupyter-notebook

Iterative Python via live Jupyter kernel (hamelnb).

NousResearch/hermes-agent · 18 tokens

paper-revision-author

Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.

opensquilla/opensquilla · 24 tokens

batch-processing-clinical-text

Run large-scale batch NER, PII extraction, or de-identification over many clinical notes on-device with OpenMed, with sharding, checkpointing, resumability, and append-only JSONL output. Use when the user needs to process a corpus or folder of notes, de-identify a dataset, run NER over thousands of documents, build a…

maziyarpanahi/openmed · 161 tokens

coding-hcc-risk-adjustment

Maps chronic conditions extracted by OpenMed to CMS-HCC V28 risk-adjustment categories and estimates a RAF (Risk Adjustment Factor) score as decision support. Use when the user wants to surface risk-adjustable diagnoses from notes, map ICD-10-CM codes to HCC categories, estimate or reconcile a patient/panel RAF, find…

maziyarpanahi/openmed · 200 tokens

coding-icd10

Suggests candidate ICD-10-CM diagnosis codes (and ICD-10-PCS procedure codes) for diagnoses and procedures extracted by OpenMed, with rationale and a human-coder caveat. Use when the user wants to code a problem list, map a diagnosis span to a billable ICD-10-CM code, route a finding to the right chapter, cross-walk…

maziyarpanahi/openmed · 209 tokens