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/verymath/ai4math-optimization/or-solvernpx skills add VeryMath/AI4Math-Optimization --skill or-solvergit clone --depth 1 https://github.com/VeryMath/AI4Math-OptimizationWhat 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 | $0.00145 | $0.05236 |
| Opus 5 | $0.00072 | $0.02618 |
| Sonnet 5 | $0.00029 | $0.01047 |
| Haiku 4.5 | $0.00015 | $0.00524 |
Grade A, and why
or-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 yesterday.
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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
运筹优化求解器统一配置
适用场景
本 skill 为以下运筹优化 skill 提供统一的求解器检测、安装与选择：
- LP（线性规划）→
../linear-programming/SKILL.md - MIP（混合整数规划）→
../mixed-integer-programming/SKILL.md - SOCP（二阶锥规划）→
../second-order-cone-programming/SKILL.md
当 LP / MIP / SOCP skill 在 Quick Start 第一步需要做环境准备时，应调用本 skill 的检测与安装流程，而非各自维护独立的求解器管理代码。
Quick Start（求解器环境准备）
核心原则：先检测，再分类，后规划。不做任何预设。
flowchart TD
DETECT["Step 1: pip list 检测所有包"]
DETECT --> DONE{" "}
DONE --> COMM{"商业求解器已安装？"}
COMM -->|是| LIC["逐个验证 License"]
LIC --> SELECT["Step 2: 综合已安装的商业 + 开源，按优先级选择"]
COMM -->|否| SELECT
SELECT --> AVAIL{"有可用求解器？"}
AVAIL -->|有| SOLVE["求解"]
AVAIL -->|无| INSTALL["Step 3: pip install 安装开源求解器（需询问用户）"]
INSTALL --> SOLVE
Step 1：统一检测
执行以下命令，一次性检测所有求解器包：
pip list | findstr -i "coptpy gurobipy mosek cplex pyscipopt highspy clarabel pulp mip ortools ecos scs cvxopt cosmo osqp swiglpk scipy lpsolve55 numpy cvxpy"
Unix 下将 findstr -i 替换为 grep -iE。
检测后，将结果分为两类：
| 类别 | 包含包 |
|---|---|
| 商业求解器（需 License） | coptpy, gurobipy, mosek, cplex |
| 开源求解器（无需 License） | scipy, highspy, pulp, cvxpy, clarabel, ecos, scs, cvxopt, cosmo, osqp, pyscipopt, mip, ortools, swiglpk, lpsolve55 |
| 基础依赖 | numpy |
Step 2：分类验证 + 选择
2a. 验证商业求解器 License（仅对已安装的）
检测到哪些商业求解器，就逐一验证哪些。不做"大概率没有"的预设——用户设备上有什么就验证什么。
对每个已安装的商业求解器，通过实际创建模型来验证 License（不能只看包是否可导入）：
| 求解器 | License 验证方式 |
|---|---|
| COPT | import coptpy as cp; cp.Envr().createModel("_t") — 抛异常则 License 缺失 |
| Gurobi | import gurobipy as gp; gp.Model("_t") — 抛异常则 License 缺失（注意：v13+ 自带受限 License，通常无需额外配置） |
| MOSEK | 通过 cvxpy 调用 prob.solve(solver=cvx.MOSEK) — 裸 mosek.Env() 可能走试用许可，但 cvxpy 调用必须要有正式 mosek.lic 文件 |
| CPLEX | 通过 cvxpy 调用 prob.solve(solver=cvx.CPLEX) — v22.1+ 自带学术 License |
验证结果：
- License 有效 → 该求解器标记为可用
- License 缺失 → 告知用户如何申请（详见「License 配置」节），将该求解器标记为不可用，继续检查其他求解器
2b. 确认问题类型
What ships with it
2 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.
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.
- yesterday First seen · 405 lines · 145 tokens per session scan A feae3bc11c1b
or-solver is a skill published in the GitHub repository VeryMath/AI4Math-Optimization (5 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 5,236 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 2026-08-31.
Other skills, from other repositories
math-beamer
Use when creating, revising, or auditing source-grounded mathematical Beamer slide decks from papers, notes, proofs, lectures, experiments, or existing LaTeX slides across pure mathematics, applied mathematics, computational mathematics, statistics, optimization, geometry, topology, algebra, number theory…
paper-writing
Use when drafting, revising, or auditing source-grounded mathematical paper text, including abstracts, introductions, related work, theorem exposition, experiment narratives, revision plans, and response letters.
latex-build-and-layout-audit
Use when checking LaTeX paper projects for compilation, latexmk logs, undefined references, citation issues, duplicate labels, macro/package hygiene, layout warnings, floats, arXiv, or venue compatibility.
proof-obligation-and-assumption-audit
Use when checking mathematical paper results for assumptions, quantifiers, domains, dependency fit, edge cases, external theorem use, proof coverage, or theorem-to-claim consistency.
claim-evidence-ledger
Use when auditing mathematical paper drafts for supported claims, missing citations, overclaims, proof status, experiment support, or source-to-text traceability.
paper-skeleton-and-logical-architecture
Use when turning mathematical notes, theorem statements, proof sketches, experiments, or reading outputs into a paper skeleton, section plan, result dependency map, or contribution architecture before prose drafting.