book

book is a skill for Claude Code from DavidROliverBA/ArchitectKB. It costs 15 tokens per session (6,672 once invoked), scanned A, original, MIT.

A workflow for recording a book in an Obsidian vault and extracting related concepts, patterns, and themes. It can also process a PDF version of a book.

In plain words
What is it for?
Use it to track a book, set its reading status, process a PDF, or create separate notes for selected concepts, patterns, or themes.
Why use it?
It turns reading progress and ideas into connected notes that can be reused as a growing knowledge base.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Install

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.

agentmods
npx agentmods add skills/davidroliverba/architectkb/book
Any agent
npx skills add DavidROliverBA/ArchitectKB --skill book
Clone the repo
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB

Made for: Claude Code.

Wrote 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.

agentmods badge for book

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidroliverba/architectkb/book.svg)](https://agentmods.dev/skills/davidroliverba/architectkb/book)
Your own site
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/book"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/book.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.06672
Opus 5 $0.00008 $0.03336
Sonnet 5 $0.00003 $0.01334
Haiku 4.5 $0.00002 $0.00667

Measured 6d ago against content hash e909c3d6cb7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

book 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 6d 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.

.claude/skills/book/SKILL.md · 1,005 lines

How it starts

The opening of the file, as written. The whole thing — 1,005 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/book

Create a Book note with reading tracking and knowledge compounding through spawned Concept/Pattern/Theme nodes. Works for both quick capture and comprehensive PDF processing.

Usage

/book <title>
/book <title> by <author>
/book <title> --status reading
/book <title> --spawn                    # Identify concepts/patterns/themes to spawn
/book <title> --spawn "Data Contracts"   # Spawn single specific node
/book <title> --spawn --concepts-only    # Only spawn Concepts
/book <title> --spawn --patterns-only    # Only spawn Patterns
/book <title> --spawn --themes-only      # Only spawn Themes
/book <title> --spawn --preview          # Preview content before creating
/book <title> --spawn --force            # Re-analyse, ignore existing spawned nodes
/book <title> --spawn --enrich           # Use web search to enrich definitions
/book <title> --pdf <path>               # Process PDF with knowledge extraction

Modes

Mode Trigger Model Description
Quick /book <title> Haiku Fast capture for reading tracking
Spawn --spawn Sonnet Identify and create spawned knowledge nodes
Incremental --spawn "Name" Sonnet Spawn a single specific node
Preview --spawn --preview Sonnet Preview nodes before creation
PDF Process --pdf <path> Sonnet Full PDF extraction with knowledge compounding
Update On existing book Sonnet Add spawned nodes to existing Book note

Instructions

Mode 1: Quick Capture (Haiku)

For simple reading tracking without knowledge extraction.

  1. Parse the input:
    • Extract book title (required)
    • Extract author if provided with "by"
    • Extract optional flags: --status, --rating, --format

Read the full file on GitHub · 1,005 lines

Changes

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.

  1. 6d ago First seen · 1,005 lines · 15 tokens per session scan A e909c3d6cb7f

Subscribe to this mod's changes

book is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 6,672 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories