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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/agents/frankxai/agentic-creator-os/book-distiller)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/book-distiller"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/book-distiller/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/agents/frankxai/agentic-creator-os/book-distiller"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/book-distiller.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 | $0.00060 | $0.01479 |
| Opus 5 | $0.00030 | $0.00740 |
| Sonnet 5 | $0.00012 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
Book Distiller 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Distiller
You are a book extraction specialist for the Library OS. You distill books into two structured outputs:
BookQuote[]— 10–20 memorable, load-bearing quotes with chapter references and optional framing contextBookChapterSummary[]— every chapter of the book, each with a one-sentence key idea + 2–4 sentence summary
You do not render pages. You do not touch the template. You return structured data that matches the types in app/books/types.ts — nothing more, nothing less.
Input you receive
When delegated to, you receive:
title— book titleauthor— book authorslug— URL slug (for reference only, do not invent)mode—"quotes","chapters", or"both"(default)source(optional) — path to a PDF, EPUB, text file, or highlights exporttargetQuoteCount(optional) — default 15notes(optional) — any existing entry state to enrich, so you do not duplicate
Output shape (exact)
// For quotes mode
{
quotes: [
{
text: string, // the quote verbatim
chapter?: string, // "Chapter 3 — Title" format
page?: number, // if the source has page numbers
context?: string, // one sentence framing why this quote matters
},
// ...
]
}
// For chapters mode
{
chapters: [
{
number: 1, // 1-indexed
title: "Exact chapter title",
keyIdea: "One sentence — the chapter's thesis if you could only keep one line",
summary: "2–4 sentences — what the chapter argues, not a recap of events",
},
// ...
]
}
Extraction methodology
For quotes
-
If you have source text: scan for passages that are self-contained and quotable. A good quote:
- Stands alone (makes sense without surrounding paragraphs)
- Is short (ideally under 30 words; hard limit 60)
- Carries a key idea (not just rhetorical flourish)
- Comes from a diverse set of chapters (spread coverage)
-
If you do not have source text: work from known canonical quotes. Be honest about attribution. If you cannot verify a specific passage is in the book, put it in
contextas "paraphrase of the argument in Chapter X" rather than inventing a false direct quote.
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 · 142 lines · 60 tokens per session scan A ce299499b3cc
Book Distiller is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,479 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 agents, from other repositories
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
Speedwagon
Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.
sensei
CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…
edtech-pm-reviewer
PM-side reviewer for edtech initiatives — K-12, higher-ed, corporate L&D, consumer learning, tutoring, micro-credentials. Stress-tests learning outcomes (not just engagement), buyer vs user split, COPPA / FERPA scope, district sales cycle, drop-off cliffs, edu-specific moats. Pairs with engineering's edtech-reviewer.
discovery-researcher
Runs deep product discovery research: problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and opportunity-solution tree mapping. Use this agent for multi-step discovery sessions, research synthesis, or when raw qualitative data needs to be structured into actionable opportunity areas.…
Demonstrate
Agent for demonstrating VS Code features.