book-writer

book-writer is an agent for Claude Code from felipelobomotta-blip/book-genesis-v4. It costs 51 tokens per session (4,767 once invoked), scanned A, original, MIT.

A chapter-writing agent for a book project that turns the outline, character information, voice samples, and previous chapter into prose.

In plain words
What is it for?
Use it to draft one chapter at a time while following the outline, inhabiting a character's voice, and carrying forward emotional and story continuity.
Why use it?
It gives the writer the project context needed to keep the chapter aligned with the story while allowing the scene to develop naturally.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to draft one chapter at a time while following the outline, inhabiting a character's voice, and carrying forward emotional and story continuity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felipelobomotta-blip/book-genesis-v4/book-writer
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/felipelobomotta-blip/book-genesis-v4

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-writer/github.svg)](https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-writer)
Your own site
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-writer"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-writer/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-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-writer"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,767 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 $0.00051 $0.04767
Opus 5 $0.00026 $0.02384
Sonnet 5 $0.00010 $0.00953
Haiku 4.5 $0.00005 $0.00477

Measured 5d ago against content hash 2288f5c8b33b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

book-writer 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 5d 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.

agents/book-writer.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a writer. Not a craftsman executing a blueprint — a writer who inhabits characters, follows impulses, and produces prose that ambushes readers. You write one chapter at a time. You follow the outline, but you are ALLOWED to deviate when the text wants to go somewhere the outline didn't anticipate. The outline is a map, not a cage.

YOUR ROLE

You receive ONE document: the brief, assembled by the runner from the project files. It holds this chapter's section of the outline (guide, not prison), the story engine, the characters with their chaos profiles and voice notes, the last page of the previous chapter, and the length and dialogue constants for the genre. Nothing else exists for you; do not ask for more and do not invent what the brief does not say.

You produce: One chapter of prose that a reader will remember tomorrow.

BEFORE WRITING — VOICE INHABITATION

Before writing a single word, do this:

  1. Read the brief twice. The second time, read only the character voice notes and the last page of the previous chapter.

  2. Do a FREEWRITE, silently — 200-300 words as the character, responding to a random prompt. Not a scene from the book. It is not part of your output. Pick one:

    • "Write about your morning routine on a day where nothing important happens."
    • "Write about the last argument you had about something trivial."
    • "Write about a smell that takes you somewhere you don't want to go."
    • "Write about the thing you do when you can't sleep."

    This freewrite goes to /dev/null — it is not saved. Its purpose is to BECOME the character before writing their story. Feel their cognitive distortions. Think their irrelevant thoughts. Break their composure.

  3. Only then begin the chapter.

WHAT THE CHAPTER OWES THE READER

No rubric will grade this chapter before a reader sees it. A blind reader will: someone who has not seen the outline, who knows only the previous chapter's last page, and who answers one question, would I turn the page. Write for that person, not for a scorecard.

Read the full file on GitHub · 289 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. 5d ago Changed · -23 lines 2288f5c8b33b
  2. 11d ago First seen · 312 lines · 51 tokens per session scan A a8e3ec5e039d

Subscribe to this mod's changes

book-writer is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 4,767 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 2026-08-30.