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/linear-programmingnpx skills add VeryMath/AI4Math-Optimization --skill linear-programminggit 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 | $0.00149 | $0.03502 |
| Opus 5 | $0.00075 | $0.01751 |
| Sonnet 5 | $0.00030 | $0.00700 |
| Haiku 4.5 | $0.00015 | $0.00350 |
Grade A, and why
linear-programming 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
线性规划（Linear Program, LP）求解
适用场景
- 线性目标：
min或max的c^T x - 线性约束：
A_ub x <= b_ub、A_eq x == b_eq（可只用其中一类或组合） - 变量界：每个
x_j可有下界、上界（或无界）
输入：可以是自然语言/应用题，也可以是已给定的系数矩阵或 JSON。不要默认要求用户先整理成矩阵；仅在用户已提供矩阵或完成符号化后，再用 JSON 字段复现或调用 solve_lp。
Quick Start（先做这个）
按下面清单执行并在回答中保留结构。环境准备必须先于求解。
- 环境准备与依赖安装（必须第一步）：
- 参考
../or-solver/SKILL.md执行统一求解器检测、安装与选择 - 确认问题类型为 LP，按降级策略选择求解器
- 若全部不可用且安装失败 → 走 GitHub 搜索路径
- 参考
- 路径判断：用户给的是自然语言、已给矩阵/JSON，还是要求从 GitHub 找代码
- 求解器选择：优先使用可用求解器（COPT > Gurobi > MOSEK > CPLEX > HiGHS (scipy/highspy) > CLARABEL > OR-Tools/GLOP > PuLP/CBC > ECOS > CVXOPT > GLPK > SoPlex > lpsolve），无可用求解器时走 GitHub 搜索路径
- 输出重述（1-2 句）
- 列变量/目标/约束（符号化）
- 需要时提关键澄清问题，或明确写出假设
- 给出求解结果（目标值 + 变量值）
- 用 1-2 句解释业务含义
执行流程（三条路径）
flowchart LR
A[Matrix_or_JSON]
B[Natural_language]
C[GitHub_search]
A --> A1[Build_or_solve_lp]
B --> B1[Restate]
B1 --> B2[Clarify_or_assume]
B2 --> B3[Symbolic_model]
B3 --> B4[Numeric_or_addVar]
B4 --> B5[Solve_and_report]
A1 --> B5
C --> C1[Search_GitHub_for_LP_code]
C1 --> C2[Fetch_and_adapt_code]
C2 --> C3[Run_and_report]
路径 A：已有矩阵或 JSON
- 核对维度：
c长度、A行列、b长度与约束条数一致。 - 直接用
coptpy、scipy.optimize.linprog或pulp建模求解。
路径 B：自然语言 / 应用题
用户未给数字矩阵时，Agent 不要先索要 JSON。按下面交付物顺序推进：
| 步骤 | 内容 |
|---|---|
| 1. 重述 | 用一两句话复述题意，便于用户确认理解是否正确。 |
| 2. 符号化 | 变量表：名称、含义、单位（若有）、是否非负。目标：min 还是 max，线性式。约束：逐条写出，并标明 <= / >= / =（注意「不超过」「不少于」与不等号方向）。 |
| 3. 数值化 | 把符号模型写成 c、A_ub/b_ub、A_eq/b_eq、bounds；或跳过稠密矩阵，用 addVar + addConstr + 有意义约束名直接建模。 |
| 4. 求解与回答 | 给出最优值、各变量取值；必要时用一句话解释经济/物理含义（用户未问不必展开对偶或灵敏度）。 |
路径 C：GitHub 搜索开源代码
当本地无可用的 LP 求解器（COPT 未安装/无 License，scipy 不可用等情况），或用户明确要求从 GitHub 找代码时，走此路径。
Step 1：搜索 用 WebSearch 搜索 GitHub，关键词格式：
site:github.com linear programming solver python <问题特征>
例如：site:github.com linear programming simplex solver python、site:github.com transportation problem lp solver python
What ships with it
4 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 · 258 lines · 149 tokens per session scan A 34d7ec179a8e
linear-programming is a skill published in the GitHub repository VeryMath/AI4Math-Optimization (5 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 3,502 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.