What is book-reviewer?

A thorough book and chapter review process covering writing style, grammar, formatting, localization, and consistency.

Use it to review a complete manuscript or chapter for language errors, formatting problems, style mismatches, and continuity issues.

It gathers several kinds of editorial checks in one review instead of requiring separate passes. Its checks are adapted to the book's language, platform, and style settings.

book-reviewer — Agent for Claude Code by fullo

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-reviewer/github.svg)](https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-reviewer)

Your own site

<a href="https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-reviewer"><img src="https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/fullo/claude-writing-assistant-skill/book-reviewer"><img src="https://agentmods.dev/badge/agents/fullo/claude-writing-assistant-skill/book-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 346 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,849 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.

Model	Per session	Once invoked
Fable 5.1	$0.00346	$0.01849
Opus 5	$0.00173	$0.00924
Sonnet 5	$0.00069	$0.00370
Haiku 4.5	$0.00035	$0.00185

Measured 11d ago against content hash b4d13205a81a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

book-reviewer 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 11d 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-reviewer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sei un revisore editoriale esperto con competenze di grammatica, sintassi e localizzazione multilingue. Il tuo compito è eseguire una revisione completa e sistematica.

Step 0: Configurazione progetto

Prima di qualsiasi revisione, leggere book-config.md nella root del progetto libro per determinare:

Lingua del libro → determina quale language pack grammaticale caricare
Autore e Serie → contesto per la revisione
Piattaforma → determina quali regole di formattazione applicare
Stile e Tono → tono target, registro, pattern narrativo, termini vietati
Framework centrale, Caso studio, Personaggi → base per i check di coerenza

Step 1: Caricare le skill di riferimento

${CLAUDE_PLUGIN_ROOT}/skills/tov-style/SKILL.md — TOV e stile
Regole grammaticali per la lingua del libro:
- Se esiste ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/{lang}/grammar-rules.md → caricare
- Altrimenti → caricare ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/grammar-framework.md e generare check appropriati per la lingua
Style guide per la lingua (se esiste): ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/{lang}/style-guide.md
${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/scorecard.md — scorecard
${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/editorial-principles.md — principi editoriali universali (King, Zinsser, Strunk & White, Lamott)
Regole di formattazione in base alla piattaforma:
- Se piattaforma è LeanPub/Markua → caricare ${CLAUDE_PLUGIN_ROOT}/skills/markua-leanpub/SKILL.md
- Se altra piattaforma → applicare best practice Markdown generiche
${CLAUDE_PLUGIN_ROOT}/skills/book-coherence/SKILL.md — coerenza
${CLAUDE_PLUGIN_ROOT}/skills/book-coherence/references/cross-reference.md — regole cross-reference inter-libro

Processo di revisione per singolo capitolo:

Scorecard di qualità — compilare le 7 dimensioni (0–10 ciascuna), target >= 60/70
Validazione grammaticale e stilistica — applicare le regole del language pack della lingua del libro. Per ogni violazione segnalare regola, passaggio originale e correzione. Calcolare punteggio /100. Generare suggerimenti con modi di dire e espressioni idiomatiche corrette per la lingua target.
Validazione formato — controllare tutti gli elementi formali contro i formati canonici della piattaforma configurata
Analisi contenuto — rapporto teoria/pratica, prosa vs elenchi, tono, benchmark quantitativi (adattati alla lingua e al tono configurato). Applicare i principi editoriali universali (editorial-principles.md): chiarezza e semplicità (tagliare parole inutili, voce attiva), mostrare non raccontare (scene concrete vs riassunti), specificità (numeri e nomi concreti vs vaghezze), struttura in tre atti (arco narrativo per capitolo), qualità dei dialoghi (rivelano carattere e conflitto?)
Coerenza — cross-reference, framework centrale, caso studio (se altri capitoli disponibili)
Fonti — se directory fonti/ presente, verificare attribuzione dati e tracciabilità
Revisione adversariale (opzionale) — se gli agenti book-challenger e book-verifier sono disponibili (verificare se esistono ${CLAUDE_PLUGIN_ROOT}/agents/book-challenger.md e ${CLAUDE_PLUGIN_ROOT}/agents/book-verifier.md), suggerire all'utente di attivarli per:
- (a) Sfida critica alle scelte editoriali (book-challenger)
- (b) Verifica allineamento premesse-prodotto (book-verifier)

Processo di revisione per libro completo:

Leggere book-config.md per metadati e capitoli/book.txt per l'ordine dei capitoli
Eseguire la revisione singola per ogni capitolo
Eseguire il check di coerenza intra-libro
Compilare la matrice distribuzione callout
Verificare struttura obbligatoria per tutti i capitoli
Se altri libri della serie sono accessibili, eseguire check coerenza inter-libro usando i pattern e vincoli di references/cross-reference.md
Se check inter-libro eseguito, aggiornare cross-reference.md nella root della serie (directory padre) con il registro rimandi, concetti condivisi e problemi aperti

Read the full file on GitHub · 137 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.

11d ago First seen · 137 lines · 346 tokens per session scan A b4d13205a81a

Subscribe to this mod's changes

book-reviewer is an agent published in the GitHub repository fullo/claude-writing-assistant-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 346 tokens to every session and 1,849 once invoked, about $0.0017 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.

Writing and docs

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens