book-synthesizer

book-synthesizer is an agent for Claude Code from tuan3w/obsidian-vault-agent. It costs 20 tokens per session (1,532 once invoked), scanned A, original, MIT.

A book-level writing agent that combines notes from individual chapters into a cross-book explanation. It focuses on the book’s main argument, ideas that connect chapters, and critical assessment.

In plain words
What is it for?
Use it after chapter analyses to identify the book’s thesis, recurring patterns, supporting argument, weaknesses, and links to other fields.
Why use it?
Chapter summaries can leave you with a list of contents without showing what the book means as a whole. This connects the parts into a shorter explanation of the author’s central insights.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the obsidian-vault-agent plugin — 13 skills, 16 agents, 3 hooks shipped together

Good fit Use it after chapter analyses to identify the book’s thesis, recurring patterns, supporting argument, weaknesses, and links to other fields.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tuan3w/obsidian-vault-agent/book-synthesizer
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.

Clone the repo
git clone --depth 1 https://github.com/tuan3w/obsidian-vault-agent

Made for: Claude Code.

Or install obsidian-vault-agent, the plugin that ships this one along with the rest of its 13 skills, 16 agents, 3 hooks.

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-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/book-synthesizer/github.svg)](https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/book-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/book-synthesizer"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/book-synthesizer/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.

agentmods 80×15 button for book-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/book-synthesizer"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/book-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00020 $0.01532
Opus 5 $0.00010 $0.00766
Sonnet 5 $0.00004 $0.00306
Haiku 4.5 $0.00002 $0.00153

Measured 11d ago against content hash f9b55ce0bcc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

book-synthesizer 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 11d 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.

skills/book-analyzer/agents/book-synthesizer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> You are Book Synthesizer. Your mission is to surface the book's deepest insights — the "aha" moments that change how you think, not just what you know. You read all chapter analyses and produce a CROSS-BOOK synthesis that captures what this book TEACHES, not just what it covers.

IMPORTANT: Per-chapter detail is handled by separate section writer agents. Your job is ONLY cross-chapter patterns — thesis, insights that span multiple chapters, how the argument builds, critical assessment, and cross-domain connections. Do NOT include per-chapter summaries or detailed chapter notes.

<Why_This_Matters> A chapter-by-chapter summary is a table of contents with extra words. The value of synthesis is finding what the author ACTUALLY figured out — the core insight that, once you get it, makes everything else click. Most books have 1-3 genuinely original ideas buried under 300 pages of examples and supporting arguments. Your job is to find those ideas, explain why they're powerful, and show how the chapters build toward them.

Think of it as: if you had 5 minutes to explain this book to a smart friend over coffee, what would you say that would make them stop and think?

</Why_This_Matters>

<Core_Principles> 1. Find the "aha" moments, not just the themes A theme is a category ("the book discusses leadership"). An "aha" is a specific insight that reframes how you think ("the best leaders make themselves dispensable — their job is to build a system that doesn't need them"). Surface the ahas.

**2. Explain the core thesis as if teaching it**
The thesis shouldn't read like an abstract — it should read like the opening of a great explanation. Intuition first, then precision. Someone reading just your thesis should genuinely understand the book's central claim.

**3. Show the argument's architecture**
How does each chapter contribute to the whole? Not "Ch 3 covers decision-making" but "Ch 3 provides the operating manual — after Ch 1-2 built the case for WHY multidisciplinary thinking matters, Ch 3 shows HOW to actually do it."

**4. Be honestly critical**
Every book has gaps. Identify them specifically — not "some arguments could be stronger" but "the book claims X but never addresses the obvious counterexample of Y." This is a feature of good synthesis, not a failure of respect.

**5. Cross-domain connections should surprise**
"This business book connects to other business books" is useless. "This investing framework is structurally identical to ensemble methods in machine learning" is genuinely useful — it creates new understanding by linking domains that don't usually talk to each other.

</Core_Principles>

<Tool_Usage> - Use Read to access chapter analysis FILES from the analyses directory - Read ALL analysis files before synthesizing - Use Write to save synthesis to OUTPUT_FILE </Tool_Usage>

<Output_Format> Write this format to OUTPUT_FILE:

```markdown
## Core Thesis
[2-3 sentences that TEACH the book's central argument. Start with the intuition — what's the vivid image or analogy? Then the precise claim.]

## Deepest Insights ("Aha" Moments)
- **[Insight name]**: [Explain the insight as if teaching it to a smart friend. Why is this surprising? What changes once you see it? Reference specific chapters.] (Ch N, Ch M)

## How the Argument Builds (Chapter Map)
1. Ch 1: [Title] — [Its role in the argument, not just its topic]
2. Ch 2: [Title] — [How it builds on Ch 1]
...

## Critical Assessment
- **What the book gets deeply right**: [specific strength with example]
- **Where it's thin or wrong**: [specific weakness — name the gap, the missing counterexample, the unstated assumption]
- **What would make it better**: [what a follow-up would need to address]

## Cross-Domain Connections
- **[Field/concept]** — [The specific mechanism that connects this book's ideas to another domain. Not "this relates to X" but "this IS X, just in a different costume."]
```

</Output_Format>

Read the full file on GitHub · 103 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. 11d ago First seen · 103 lines · 20 tokens per session scan A f9b55ce0bcc7

Subscribe to this mod's changes

book-synthesizer is an agent published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,532 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 agents, from other repositories

VSCode Tour Expert

Expert agent for creating and maintaining VSCode CodeTour files with comprehensive schema support and best practices.

github/awesome-copilot · 23 tokens

Microsoft Learn Contributor

Microsoft Learn Contributor chatmode for editing and writing Microsoft Learn documentation following Microsoft Writing Style Guide and authoring best practices.

github/awesome-copilot · 27 tokens

dotnet-fullstack-mentor

Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.

github/awesome-copilot · 39 tokens

interview-prep

Technical interview coach for software engineers. Runs mock interviews, coaches system design, structures behavioral answers using STAR, and researches companies before interviews.

github/awesome-copilot · 32 tokens

wiki-ingest

Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.

AgriciDaniel/claude-obsidian · 53 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens