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 skills add Arcadi4/nerdy --skill b-treesgit clone --depth 1 https://github.com/Arcadi4/nerdyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arcadi4/nerdy/b-trees)<a href="https://agentmods.dev/skills/arcadi4/nerdy/b-trees"><img src="https://agentmods.dev/badge/skills/arcadi4/nerdy/b-trees/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arcadi4/nerdy/b-trees"><img src="https://agentmods.dev/badge/skills/arcadi4/nerdy/b-trees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00050 | $0.04802 |
| Opus 5.5 | $0.00020 | $0.01921 |
| Sonnet 5.5 | $0.00010 | $0.00960 |
| Haiku 4.5 | $0.00005 | $0.00480 |
Grade A, and why
b-trees 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 1mo 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B-Trees
Overview
B-trees are not just high-fanout binary search trees. They teach the external-memory index mindset: choose node size from the block-transfer model, keep height small by packing many ordered separator keys per node, and spend CPU inside a block to avoid extra disk or page accesses.
When applying this chapter in industrial contexts, answer both questions:
- Is the bottleneck disk, SSD page, cache block, or CPU comparison work?
- Which invariant prevents an insertion or deletion from needing to backtrack up the tree?
Shared CLRS Conventions
Also follow the parent clrs skill for mathematical formatting, theorem preconditions, proof tone, and chapter-skill routing. Put formal bounds in display LaTeX blocks, not inline prose or Markdown table cells.
When to Use
Use this skill for:
- B-trees, B-plus-trees, B-star-trees, external-memory indexes, database indexes, storage-engine pages, disk blocks, SSD page access, and high-fanout search trees.
- B-tree definition questions: minimum degree, key counts, child counts, sorted separator keys, equal leaf depth, and root exceptions.
B-TREE-SEARCH,B-TREE-CREATE,B-TREE-INSERT,B-TREE-SPLIT-CHILD,B-TREE-SPLIT-ROOT,B-TREE-INSERT-NONFULL, andB-TREE-DELETEreasoning.- Comparing B-trees with red-black trees, binary search trees, sorted arrays, hash tables, LSM trees, or platform ordered containers.
- 2-3-4 tree questions, including join and split exercises.
- Disk-access versus CPU-time accounting, including block read models and root residency.
Do not use this skill as the primary guide for:
- Exact lookup with no ordering, range scan, predecessor, successor, or storage-page need; prefer hash-table reasoning.
- In-memory ordered maps where a standard library tree, skip list, sorted vector, or cache-aware container already solves the problem.
- Production database implementation details not present in the chapter, such as concurrency control, write-ahead logging, crash recovery, prefix compression, B-link trees, or LSM compaction policy.
- B-plus-tree leaf-chain semantics unless the prompt explicitly asks for the variant; the chapter's base B-tree keeps satellite information with keys.
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.
- 1mo ago First seen · 369 lines · 50 tokens per session scan A 742184407d33
b-trees is a skill published in the GitHub repository Arcadi4/nerdy (6 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 4,802 once invoked, about $0.0002 per session on Opus 5.5. 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
postgresql-psql
Comprehensive guide for PostgreSQL psql - the interactive terminal client for PostgreSQL. Use when connecting to PostgreSQL databases, executing queries, managing databases/tables, configuring connection options, formatting output, writing scripts, managing transactions, and using advanced psql features for database…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…