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/augmenting-data-structuresnpx skills add Arcadi4/nerdy --skill augmenting-data-structuresgit 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 | $0.00050 | $0.03956 |
| Opus 5 | $0.00025 | $0.01978 |
| Sonnet 5 | $0.00010 | $0.00791 |
| Haiku 4.5 | $0.00005 | $0.00396 |
Grade A, and why
augmenting-data-structures 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Augmenting Data Structures
Overview
Augmenting a data structure is not "add a cached field and hope." The reusable move is to choose a base structure whose ordinary operations already fit the access pattern, add metadata whose dependencies are local enough to maintain, prove mutation updates preserve it, and only then design new queries that safely exploit it.
For production use, treat the textbook structures as proof patterns and API design warnings. Prefer mature ordered containers, database range indexes, exclusion constraints, or tested libraries unless the custom metadata and workload justify owning rotations, deletion, concurrency, persistence, and rebuild logic.
Shared CLRS Conventions
Follow the parent clrs skill for mathematical formatting, formula-free headings, direct polished answers, and CLRS-wide answer style. Keep identities, inequalities, bounds, and recurrence-like claims in display LaTeX blocks rather than inline prose.
When to Use
Use this skill for:
- Designing or reviewing augmented dynamic sets, especially red-black trees with per-node metadata.
- Order-statistic trees,
OS-SELECT,OS-RANK, select-by-rank, rank-by-handle, inversion counting, Josephus-style rank deletion, or multiset rank APIs. - Interval trees, interval overlap search, booking conflict detection, rectangle sweep-line active sets, or endpoint-overlap reasoning.
- Applying the red-black-tree augmentation theorem and checking whether a candidate attribute is locally maintainable.
- Explaining why rotations can update metadata locally and why some metadata depends on ancestors instead.
Do not use this skill merely because code contains cached fields. Use ordinary implementation judgment unless the cache is maintained across dynamic-set mutations and participates in asymptotic query behavior or proof obligations.
The Four-Step Augmentation Method
Use this as the default design and review checklist:
- Choose the underlying structure. It should already support the ordering, search, insertion, deletion, and traversal pattern needed by the application.
- Choose the extra information. Define exactly what each field means, including sentinel or empty-subtree values.
- Verify maintainability. Show how every modifying operation updates the field without breaking the claimed bound, especially rotations and deletion moves.
- Develop the new operations. Prove the query uses the metadata safely; do not assume pruning is safe because it is intuitive.
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 · 289 lines · 50 tokens per session scan A def24a802d72
augmenting-data-structures is a skill published in the GitHub repository Arcadi4/nerdy (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 3,956 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。.