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/mantou6666/math-modeling-agent-flow/math-modeling-solvernpx skills add mantou6666/Math-Modeling-Agent-Flow --skill math-modeling-solvergit clone --depth 1 https://github.com/mantou6666/Math-Modeling-Agent-FlowWrote 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/mantou6666/math-modeling-agent-flow/math-modeling-solver)<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>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 | $0.00138 | $0.06947 |
| Opus 5 | $0.00069 | $0.03474 |
| Sonnet 5 | $0.00028 | $0.01389 |
| Haiku 4.5 | $0.00014 | $0.00695 |
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.
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 — 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。
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.
- agents/openai.yaml 767 B
- CHANGELOG.md 1.3 KB
- evals/anti_fixation/cases.json 3.3 KB
- evals/anti_fixation/README.md 157 B
- evals/maintainer_experience_cases.jsonl 7.2 KB
- evals/rc2_behavioral_regressions.md 5.4 KB
- evals/trigger_cases.csv 2.3 KB
- LICENSE 1.0 KB
- PACKAGE_MANIFEST.json 15 KB
- README.md 3.7 KB
- references/core/execution-certification.md 1.4 KB
- references/core/experiment-audit.md 623 B
- references/core/handoff.md 1.1 KB
- references/core/idea-space.md 1.8 KB
- references/core/method-choice.md 2.3 KB
- references/core/multi-question-flow.md 1020 B
- references/core/portable-artifacts.md 916 B
- references/core/problem-framing.md 2.4 KB
- references/core/question-packet.md 734 B
- references/core/research-gateway.md 3.0 KB
- references/core/runtime-capabilities.md 4.7 KB
- references/core/search-control.md 1.1 KB
- references/core/validation-design.md 1.7 KB
- references/implementation-starters/matlab/evolutionary_search_starter.m 271 B
- references/implementation-starters/matlab/multicriteria_starter.m 456 B
- references/implementation-starters/matlab/ode_starter.m 160 B
- references/implementation-starters/matlab/tabular_baseline_starter.m 178 B
- references/implementation-starters/python/decision/multicriteria_starter.py 808 B runs code
- references/implementation-starters/python/learning/tabular_baseline_starter.py 861 B runs code
- references/implementation-starters/python/learning/time_series_backtest_starter.py 678 B runs code
- references/implementation-starters/python/optimization/evolutionary_search_starter.py 600 B runs code
- references/implementation-starters/python/optimization/milp_starter.py 806 B runs code
- references/implementation-starters/python/optimization/monte_carlo_starter.py 518 B runs code
- references/implementation-starters/python/optimization/network_flow_starter.py 651 B runs code
- references/implementation-starters/python/simulation/ode_starter.py 534 B runs code
- references/implementation-starters/README.md 781 B
- references/method-atlas/evaluation-ranking.md 715 B
- references/method-atlas/mechanistic-simulation.md 788 B
- references/method-atlas/optimization.md 1.2 KB
- references/method-atlas/search-diagnostics.md 509 B
- references/method-atlas/statistical-learning.md 1.1 KB
- references/scenario-patterns/classification.md 470 B
- references/scenario-patterns/data-inference.md 607 B
- references/scenario-patterns/dynamic-systems.md 476 B
- references/scenario-patterns/environment-systems.md 426 B
- references/scenario-patterns/evaluation-decision.md 429 B
- references/scenario-patterns/forecasting.md 489 B
- references/scenario-patterns/geometry-paths.md 480 B
- references/scenario-patterns/networked-systems.md 538 B
- references/scenario-patterns/policy-strategy.md 448 B
- references/scenario-patterns/scheduling-allocation.md 528 B
- schemas/artifact-lock.schema.json 655 B
- schemas/budget-ledger.schema.json 1.2 KB
- schemas/dependency-graph.schema.json 1.1 KB
- schemas/examples/artifact-lock.example.json 485 B
- schemas/examples/budget-ledger.example.json 309 B
- schemas/examples/dependency-graph.example.json 396 B
- schemas/examples/execution-record.example.json 1.3 KB
- schemas/examples/frontier-map.example.json 1.3 KB
- schemas/examples/question-checkpoint.example.json 570 B
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.
- 6d ago First seen · 315 lines · 138 tokens per session scan A 12be6403ff12
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.
Other skills, from other repositories
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
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…
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…
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…