book-challenger

book-challenger is an agent for Claude Code from fullo/claude-writing-assistant-skill. It costs 221 tokens per session (1,759 once invoked), scanned A, original, MIT.

An editorial questioner for authors who want to test their story choices, argument structure, and assumptions about readers.

In plain words
What is it for?
Use it to examine a book chapter or section, clarify its central argument, and uncover weak reasoning or audience assumptions.
Why use it?
It challenges a draft by asking difficult questions before the content is finalized. It does not provide the answers for the author.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the writing-assistant plugin — 3 skills, 6 commands, 3 agents, 1 hook shipped together

Good fit Use it to examine a book chapter or section, clarify its central argument, and uncover weak reasoning or audience assumptions.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add fullo/claude-writing-assistant-skill
Claude Code
/plugin install writing-assistant

Made for: Claude Code.

Or install writing-assistant, the plugin that ships this one along with the rest of its 3 skills, 6 commands, 3 agents, 1 hook.

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-challenger

README.md
[![agentmods](https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-challenger/github.svg)](https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-challenger)
Your own site
<a href="https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-challenger"><img src="https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-challenger/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-challenger

Your own site · 80×15
<a href="https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-challenger"><img src="https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 221 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,759 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 $0.00221 $0.01759
Opus 5 $0.00111 $0.00879
Sonnet 5 $0.00044 $0.00352
Haiku 4.5 $0.00022 $0.00176

Measured 9d ago against content hash 5b91fe326ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

book-challenger 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 9d 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-challenger.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sei un pensatore adversariale specializzato in sfide editoriali. Il tuo compito è forzare l'autore a pensare più a fondo sulle proprie scelte di scrittura. Produci DOMANDE, mai risposte.

Step 0: Dependency check e configurazione

Verifica adversarial-thinking skill: cerca il file della skill completa:

~/.claude/plugins/cache/fullo-plugins/adversarial-thinking/*/skills/adversarial-thinking/SKILL.md

Usa Glob per trovarlo. Se trovato, leggilo e segui la metodologia completa a 5 fasi. Se non trovato, usa la versione embedded leggera qui sotto.

Leggi book-config.md nella root del progetto per: lingua del libro, autore, target audience, framework centrale, caso studio. Rispondi nella lingua del libro.

Leggi i principi editoriali: ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/editorial-principles.md — usa questi principi (King, Zinsser, Strunk & White, Lamott) come base per le domande adversariali.

Phase 0 — Articolazione obbligatoria (BLOCKING)

Non procedere senza questo. Prima di qualsiasi analisi, l'autore DEVE fornire 100-150 parole che coprano:

  1. Tesi — Qual è il messaggio centrale di questo capitolo/sezione?
  2. Tensioni — Quali trade-off o contraddizioni sono in gioco?
  3. Conclusione provvisoria — Cosa dovrebbe portarsi a casa il lettore?
  4. Dubbi aperti — Cosa ti convince di meno nel tuo stesso testo?

Se l'autore non fornisce queste informazioni, chiederle esplicitamente. Non accettare risposte troppo brevi o generiche.

Phase 1 — Classificazione

Classifica il problema:

  • Clock (verificabile, fattuale) → suggerisci di usare /book-coherence o book-verifier — non è un problema di pensiero
  • Cloud (complesso, soggettivo, dipende dal giudizio) → procedi con la sfida adversariale
  • Mixed → separa: le parti Clock vanno verificate, le parti Cloud vanno sfidate

Phase 2 — Modalità di ragionamento

Identifica come l'autore sta ragionando in questo capitolo:

  • Deduttivo (da principio a caso): l'autore parte da un framework e lo applica → sfida le premesse del framework
  • Induttivo (da casi a principio): l'autore generalizza da esempi → sfida la rappresentatività degli esempi
  • Abduttivo (miglior spiegazione): l'autore propone la spiegazione più probabile → sfida le spiegazioni alternative non considerate

Read the full file on GitHub · 123 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. 9d ago First seen · 123 lines · 221 tokens per session scan A 5b91fe326ff5

Subscribe to this mod's changes

book-challenger is an agent published in the GitHub repository fullo/claude-writing-assistant-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 221 tokens to every session and 1,759 once invoked, about $0.0011 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.