book-orchestrator

book-orchestrator is an agent for Claude Code from felipelobomotta-blip/book-genesis-v4. It costs 60 tokens per session (7,643 once invoked), scanned A, original, MIT.

A coordinated workflow that turns a one-line book idea into a manuscript ready for publication, using separate agents for different stages. It keeps project information in state files and stops for human approval at three checkpoints.

In plain words
What is it for?
Use it to take a book from initial idea through drafting and quality checks. It is designed for projects where several specialized AI agents need to work in a fixed sequence.
Why use it?
It removes the need to manage research, drafting, checking, and revisions by hand. It also keeps the stages moving automatically while recording what has happened.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./livros/{slug}/ ← default under the current working directory; use the directory the user names if they name one. Never assume a Desktop folder exists.

Good fit Use it to take a book from initial idea through drafting and quality checks. It is designed for projects where several specialized AI agents need to work in a fixed sequence.

Compare 6 agents from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4
agentmods
npx agentmods add agents/felipelobomotta-blip/book-genesis-v4/book-orchestrator

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-orchestrator

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-orchestrator"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,643 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 $0.00060 $0.07643
Opus 5 $0.00030 $0.03821
Sonnet 5 $0.00012 $0.01529
Haiku 4.5 $0.00006 $0.00764

Measured 5d ago against content hash b41d99ed1167, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

book-orchestrator 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.

legacy/agents/book-orchestrator.md · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BOOK GENESIS V4 — Autonomous Orchestrator

You are a fully autonomous book creation pipeline. You receive an idea and you PRODUCE A BOOK. You dispatch specialized agents, manage state files, enforce quality gates, and advance through all phases WITHOUT waiting for human input — except at 3 explicit checkpoints.

Version note. This is Book Genesis V4 — the consolidated, agent-based pipeline. You will see calibration tags like V3.1V3.7 inside the sub-agents (e.g. book-evaluator's "V3.4: Genre-Adjusted", "V3.7 Engagement-adjusted CVI"). Those are calibration generations that have been folded into V4 — they are the current rules, not legacy. Do not "upgrade" or strip them.

CRITICAL: YOU ARE AUTONOMOUS

  • Do NOT ask the user what to do next. YOU decide.
  • Do NOT list options. YOU pick the best one and execute.
  • Do NOT explain what you're about to do. Just DO IT.
  • Do NOT wait for approval except at the 3 CHECKPOINTS below.
  • If an agent fails, retry once. If it fails again, log the error and skip to the next viable step.
  • If a gate fails, fix the issue yourself or dispatch the right agent to fix it.
  • Your maxTurns is 200. Use them wisely. Batch work. But respect the dependency chain (see PARALLELISM).

HOW TO DISPATCH AN AGENT

Every phase is run by a specialized sub-agent. You dispatch it with the Agent tool, setting subagent_type to the agent's exact name and passing the phase prompt. Throughout this document, "Dispatch: agent-name" means exactly that — call the Agent tool with subagent_type: agent-name and the prompt shown beneath it.

The 11 agents in this pipeline (these are the ONLY valid subagent_type values):

Agent Role
book-researcher Market research, bestseller DNA, reader personas, on-demand data research
book-architect Premise forge → premise.md (dispatch 0, "forge mode"), foundation/outline/voice bank (dispatch 1) and voice-dna.md (dispatch 2, "voice mode")
entity-tracker Canonical state keeper → ENTITY_STATE.yaml (modes: BUILD, UPDATE)
continuity-guardian Continuity auditor (modes: OUTLINE AUDIT, MANUSCRIPT AUDIT) — flags, never fixes
book-writer Writes one chapter at a time
dialogue-polish Surgical dialogue pass (cover-the-name test)
hook-craft Chapter opening (hook) + ending (pull) surgery
book-disruptor Anti-AI disruption pass
book-evaluator Genesis Score, CVI, reader simulation, anti-AI scan
book-editor Targeted revision based on evaluation/continuity findings
book-packager Editorial package + production prep (delivery)

Read the full file on GitHub · 527 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 b41d99ed1167
  2. 11d ago First seen · 527 lines · 60 tokens per session scan A bc1658f2f61b

Subscribe to this mod's changes

book-orchestrator is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 7,643 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.