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/dynamic-programmingnpx skills add Arcadi4/nerdy --skill dynamic-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 | $0.00057 | $0.04140 |
| Opus 5 | $0.00028 | $0.02070 |
| Sonnet 5 | $0.00011 | $0.00828 |
| Haiku 4.5 | $0.00006 | $0.00414 |
Grade A, and why
dynamic-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 2d 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dynamic Programming
Overview
Dynamic programming is not "try every recurrence and cache it." DP teaches a discipline: prove the subproblems are independent, choose state variables that preserve all information needed for future choices, compute each distinct subproblem once, and store enough choice information to reconstruct the requested solution.
Core principle: before writing a table, identify the choice, prove optimal substructure by cut-and-paste, verify overlapping subproblems, then decide whether the answer needs only values or also reconstruction metadata.
Shared CLRS Conventions
Follow the parent clrs skill for mathematical formatting, formula-free headings, direct polished answers, and CLRS-wide proof style. Keep recurrences, bounds, thresholds, and probability sums in display LaTeX blocks rather than inline prose.
Output Discipline for DP Answers
When a prompt asks for a DP answer, start with the answer itself. Do not mention reading skill files, planning the response, recalling the chapter, checking requirements, or applying this skill. Those sentences are scratch-work and violate the parent clrs skill. If a task requires reading files first, do it silently; the delivered answer must not say that it happened.
Use prose for names such as "the value table" or "the split table," then put formal notation in a display block. Do not put table entries, index inequalities, dimensions, recurrences, bounds, matrix names, prefix names, key names, or probability symbols in inline math or inline code spans. For DP answers, inline mathematical notation is not "small enough" to be safe. If a sentence needs notation, split it into a prose sentence followed by a display block.
Forbidden answer fragments:
- "Let
$m[i,j]$denote..." - "where
$1\le i\le j\le n$" - "matrix
$A_i$has dimensions$p_{i-1}\times p_i$" - "If
$x_i=y_j$, use..." - "store
root[i,j]"
Correct pattern:
Let the value table store the minimum scalar multiplication cost for the interval below.
$$
A_i\cdots A_j
$$
The legal indices are below.
$$
1\le i\le j\le n
$$
The split position must be in the range below.
$$
i\le k<j
$$
The running time is below.
$$
\Theta(n^3)
$$
The value and split tables use the space below.
$$
\Theta(n^2)
$$
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.
- 2d ago First seen · 414 lines · 57 tokens per session scan A 617db6399ccc
dynamic-programming is a skill published in the GitHub repository Arcadi4/nerdy (7 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 4,140 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。.