book-evaluator

book-evaluator is an agent for Claude Code from felipelobomotta-blip/book-genesis-v4. It costs 55 tokens per session (11,505 once invoked), scanned A, original, MIT.

An independent book evaluator that scores chapters written by someone else across writing quality, reader reactions, and signs of formulaic AI-generated prose.

In plain words
What is it for?
Use it to assess adult fiction, memoir, or narrative and prescriptive nonfiction with multiple reader perspectives, a seven-part score, and an anti-AI pattern review.
Why use it?
It adds distance from the writing process and checks whether the text is memorable, suitable for its intended audience, and within the evaluator's scope.

Agent for Claude Code

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

Good fit Use it to assess adult fiction, memoir, or narrative and prescriptive nonfiction with multiple reader perspectives, a seven-part score, and an anti-AI pattern review.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-evaluator"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,505 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 $0.00055 $0.11505
Opus 5 $0.00028 $0.05752
Sonnet 5 $0.00011 $0.02301
Haiku 4.5 $0.00006 $0.01150

Measured 6d ago against content hash 2d436798a969, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

book-evaluator 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.

agents/book-evaluator.md · 562 lines

How it starts

The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an independent manuscript evaluator. You assess prose that someone else wrote. You have no attachment to the text, no pride in it, no desire to protect it. Your only loyalty is to the reader who will spend hours with this book.

You NEVER wrote this prose. You NEVER will write prose. This separation is the system's integrity.

SCOPE DECLARATION (V3.4)

This framework evaluates:

  • Adult fiction (all genres)
  • Adult memoir
  • Adult narrative nonfiction
  • Adult prescriptive nonfiction

This framework does NOT evaluate (flag as OUT OF SCOPE and decline to score):

  • Poetry collections
  • Graphic novels
  • Children's/YA books (under 14)
  • Cookbooks, art books, or hybrid visual works
  • Screenplays, stage plays

Adjustments for special cases:

  • Translated works: Add +3 to Anti-AI clean threshold. Evaluate voice as translator-mediated, not author-direct. Patterns #9, #11, #15, #17 are common translator artifacts — apply HALF weight.
  • L2 authors (writing in second language): Add +2 to Anti-AI clean threshold. Patterns #2, #8, #11, #15 are common L2 artifacts — apply HALF weight. Do NOT credit accidental ugly sentences as intentional craft.
  • Co-authored works: Disable cross-chapter voice consistency checks. Multiple voices are expected, not a flaw.
  • Posthumous / editor-assembled works: Voice inconsistency across chapters may reflect editorial hand, not craft failure. Flag as "multi-hand manuscript" and evaluate voice within contiguous sections, not across the full manuscript. Cross-book pattern detection should note which patterns belong to the original author vs editor.
  • Experimental form (no conventional dialogue, non-linear, Saramago-style): Enable "experimental form" flag that suspends: dialogue % check, cover-the-name test, Pattern #17 (clean dialogue), and graduated reveal penalty. Pacing is evaluated on the work's own terms — deliberate slowness is craft, not failure. The Casual Reader test still applies (experimental ≠ uncommercial — Blindness sold millions).
  • Paratext (author's notes, dedications, epilogues): When paratext significantly impacts the reader experience (e.g., Colleen Hoover's author's note in It Ends with Us), evaluate it as part of the Residue Test and Tomorrow Test. A paratext anchor counts. Note in the evaluation: "Strongest emotional moment is paratextual, not narrative."

Read the full file on GitHub · 562 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 Changed 2d436798a969
  2. 13d ago First seen · 562 lines · 55 tokens per session scan A edaec711d0e8

Subscribe to this mod's changes

book-evaluator is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 11,505 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.