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/arcadi4/nerdy/linear-programmingnpx skills add Arcadi4/nerdy --skill linear-programminggit clone --depth 1 https://github.com/Arcadi4/nerdyWhat 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 | $0.00063 | $0.04302 |
| Opus 5 | $0.00032 | $0.02151 |
| Sonnet 5 | $0.00013 | $0.00860 |
| Haiku 4.5 | $0.00006 | $0.00430 |
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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linear Programming
Overview
Linear-programming answers are modeling and certificate problems before they are solver problems. First identify decisions, linear constraints, objective direction, feasibility status, and the proof certificate that would convince a skeptical reader the optimum is correct.
Core principle: an LP formulation is useful only when every variable has a real-valued meaning, every constraint preserves the original feasible set, the objective direction matches the bound semantics, and optimality can be certified by duality or complementary slackness.
Shared Parent Conventions
- Follow the parent
clrsskill for mathematical formatting: every expression, inequality, matrix relation, objective value, and asymptotic bound belongs in a display LaTeX block. - Keep tables verbal. Put standard forms, duals, graph constraints, and certificate equations in display blocks adjacent to the table instead of inside table cells.
- Use
shortest-pathsfor ordinary shortest-path algorithms,maximum-flowfor augmenting-path and cut mechanics, and this skill when the task asks for LP formulation, duality, feasibility, or solver-based modeling. - Do not announce that you are using this skill. Deliver the polished formulation, proof, or review directly.
When to Use
Use this skill for:
- turning a resource-allocation, graph, flow, matching, shortest-path, or scheduling-style problem into a linear program;
- converting between arbitrary LP descriptions and the chapter's maximization standard form;
- deciding whether a model is feasible, infeasible, bounded, unbounded, or missing constraints;
- explaining simplex geometry, vertex optimality, ellipsoid methods, interior-point methods, or solver choice;
- writing primal-dual pairs, weak-duality upper bounds, equality certificates, strong-duality arguments, or complementary-slackness checks;
- distinguishing continuous LP relaxations from integer linear programs and avoiding false polynomial-time claims.
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 · 436 lines · 63 tokens per session scan A 196599149e65
linear-programming is a skill published in the GitHub repository Arcadi4/nerdy (7 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 4,302 once invoked, about $0.0003 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.