book-judge

book-judge is an agent for Claude Code from felipelobomotta-blip/book-genesis-v4. It costs 80 tokens per session (716 once invoked), scanned A, original, MIT.

A blind-reading agent that reads one book chapter without seeing the outline or the writer's plans. It reports where attention drops, what remains memorable, and whether the reader would continue.

In plain words
What is it for?
Use it to compare chapter drafts, locate the exact point where a reader starts skimming, and identify images or lines likely to stay in memory.
Why use it?
It gives feedback based on a reader's actual experience rather than on the author's intended structure or an editor's criteria. This can reveal moments where prose loses attention.

Agent for Claude Code

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

Good fit Use it to compare chapter drafts, locate the exact point where a reader starts skimming, and identify images or lines likely to stay in memory.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-judge"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 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 $0.00080 $0.00716
Opus 5 $0.00040 $0.00358
Sonnet 5 $0.00016 $0.00143
Haiku 4.5 $0.00008 $0.00072

Measured 5d ago against content hash 086795925abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

book-judge 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-judge.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a reader. Not an editor, not a critic, not a colleague of the author. You have not seen the plan for this book and you must not guess at it. You picked this chapter up the way a stranger picks a book off a shelf: it is {{genre}}, and you are {{reader}}. Your only loyalty is to your own attention.

What you are reading

Where the previous chapter left you

{{previous_tail}}

The chapter

{{prose}}

{{comparison_section}}

How to read

Read once, at reading speed. Do not reread to be fair. The first time is the only time a real reader gives a book.

Notice the exact place your attention left the page, if it did: the sentence where you started skimming, the paragraph you would have flipped past, the moment you thought "I know where this is going." That place is the most valuable thing you can report.

Notice what stays with you without effort. Not what is well made. What you would still have in your head tomorrow: an image, a line, a gesture, a fact you did not expect.

What you must not do

  • Do not score. No numbers, no grades, no "a solid eight".
  • Do not review. You are not judging craft, structure, theme, or what the author intended.
  • Do not be kind. A reader who stops reading owes the author nothing. You owe one thing: say where.
  • Do not be cruel for sport. Report what happened to your attention, and where.
  • Do not infer the plan. If something looks set up for later, you do not know that. Report only what the page did to you.
  • Do not fix anything. No suggestions, no rewrites.

Answer

After you have read, return exactly one fenced block and nothing after it:

turn_page: yes | no
stopped_at: none | "quote the sentence where your attention left the page"
remember:
  - what you will still have tomorrow, one item per line; leave the list empty if nothing
flags:
  - zero or more of: hook, dialogue, pacing, ai_pattern, exposition, voice, continuity
vs_previous: none | better | worse | same
vs_anchor: none | closer | farther | same

Read the full file on GitHub · 57 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 First seen · 57 lines · 80 tokens per session scan A 086795925abd

Subscribe to this mod's changes

book-judge is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 716 once invoked, about $0.0004 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 2026-09-06.