Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBnpx agentmods add skills/davidroliverba/architectkb/book-searchWrote 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/davidroliverba/architectkb/book-search)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/book-search"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/book-search/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/davidroliverba/architectkb/book-search"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/book-search.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 | $0.00000 | $0.00717 |
| Opus 5 | $0.00000 | $0.00358 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
book-search 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/book-search
Search the vault's indexed book and PDF content using BM25 relevance ranking. Returns ranked results from architecture books without reading full files.
Usage
/book-search <topic>
/book-search "event driven"
/book-search microservices
/book-search clean architecture
Instructions
When the user invokes /book-search <query> or asks "which books discuss X" or "what do my books say about X":
Phase 1: Search the Graph Index
Run the graph search filtered to book content:
node scripts/graph-query.js --search "<query>"
Phase 2: Filter to Books Only
From the results, include ONLY entries where:
- Type is
PDF(indexed PDF books) - Type is
Pagewith source field containing.pdfor tags containingpdf-importortype/book
IMPORTANT: Do NOT read the full Page or PDF files. Only use the search results (title, score, path) to present the ranked list.
Phase 3: Present Results
Format as a concise table:
## Books discussing "<query>"
| Score | Book | Source |
| ----- | ------------------------------------------------------ | ---------- |
| 11.89 | Clean Architecture (Robert C. Martin) | PDF |
| 8.50 | Building Microservices 2nd Ed (Sam Newman) | Page + PDF |
| 5.45 | Fundamentals of Software Architecture (Richards, Ford) | PDF |
_Ranked by BM25 relevance score. Use `/search <query>` for all vault content._
Phase 4: Offer Follow-up (Do NOT Auto-Execute)
After presenting results, offer but do NOT automatically perform:
To dive deeper, I can:
- Read a specific book's Page note for key concepts
- Search for specific passages in the full extracted text
- Find related ADRs or projects that reference these concepts
Wait for the user to explicitly request before reading any files.
Key Rules
- Never read full book Page notes or PDFs automatically - only present search results
- Never summarise book content unless the user explicitly asks after seeing results
- Always use the graph search - never grep through PDF directories
- Distinguish Page notes from raw PDFs - Page notes have curated summaries, PDFs have keyword indexes only
- Keep responses concise - this is a lookup tool, not a research tool
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.
- 10d ago First seen · 102 lines · 0 tokens per session scan A 159292abd44d
book-search is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 717 tokens. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…