book-review

book-review is a command for Claude Code from fullo/claude-writing-assistant-skill. It costs 10 tokens per session (805 once invoked), scanned A, original, MIT.

A command that performs a full editorial review of a book chapter using the project's language, style, tone, and publishing settings.

In plain words
What is it for?
For scoring and improving a chapter's language, structure, tone, and Leanpub Markua formatting when that platform is configured.
Why use it?
It brings grammar, formatting, and editorial checks into one review process instead of relying on separate manual checks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

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 For scoring and improving a chapter's language, structure, tone, and Leanpub Markua formatting when that platform is configured.

Compare 6 commands 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-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/fullo/claude-writing-assistant-skill/book-review"><img src="https://agentmods.dev/badge/commands/fullo/claude-writing-assistant-skill/book-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 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 $0.00010 $0.00805
Opus 5 $0.00005 $0.00402
Sonnet 5 $0.00002 $0.00161
Haiku 4.5 $0.00001 $0.00081

Measured 10d ago against content hash 75908aff1ac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

book-review 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 10d 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.

commands/book-review.md · 62 lines

What it actually says

Esegui una revisione editoriale completa del capitolo in @$1.

Step 0: Configurazione lingua e stile

Leggere book-config.md nella root del progetto per determinare:

  • Lingua → quale language pack grammaticale caricare
  • Piattaforma → quali regole di formattazione applicare
  • Stile e Tono → tono target, registro, rapporto teoria/pratica

Caricare le skill di riferimento:

  • ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/SKILL.md per il TOV e lo stile
  • Regole grammaticali: ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/{lang}/grammar-rules.md (dove {lang} è la lingua da book-config.md). Se il pack non esiste, usare ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/grammar-framework.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/scorecard.md per la scorecard
  • ${CLAUDE_PLUGIN_ROOT}/skills/tov-style/references/editorial-principles.md per i principi editoriali (King, Zinsser, Strunk & White, Lamott)
  • Se piattaforma è LeanPub/Markua: ${CLAUDE_PLUGIN_ROOT}/skills/markua-leanpub/SKILL.md per le regole formato

Eseguire nell'ordine:

1. Scorecard di qualità (7 dimensioni, punteggio 0–10 ciascuna) Compilare la scorecard completa. Obiettivo: >= 60/70.

2. Validazione grammaticale e stilistica Verificare il capitolo contro le regole del language pack della lingua configurata. Per ogni violazione:

[R#] Riga/passaggio: "testo originale"
  → Correzione: "testo corretto"

Generare correzioni con modi di dire e espressioni idiomatiche naturali della lingua target. Concludere con punteggio di conformità /100.

3. Validazione formato Se la piattaforma è LeanPub/Markua: controllare tutti gli elementi formali (epigrafe, separatore, sezioni, pagebreak, callout, Quick Win, Checkpoint). Se altra piattaforma: applicare best practice Markdown generiche.

4. Check contenuto

  • Rapporto teoria/pratica (target da book-config.md, default 30/70)
  • Prosa vs elenchi puntati (segnalare elenchi narrativi da convertire)
  • Tono coerente con quello configurato (segnalare passaggi che deviano)
  • Benchmark quantitativi (adattati alla lingua e al tono)

5. Riepilogo finale Presentare (nella lingua del libro):

  • Scorecard compilata
  • Punteggio conformità grammaticale /100
  • Top 5 interventi prioritari con riga e proposta di correzione
  • Giudizio complessivo: pronto per pubblicazione / necessita revisione mirata / necessita revisione approfondita

Git commit

Se sono state applicate correzioni al testo e ci si trova in un repository git (git rev-parse --is-inside-work-tree 2>/dev/null), eseguire:

git add * && git commit -m "book-review: editorial review [nome-file] — scorecard [punteggio]/70, grammar [punteggio]/100"

Se non ci si trova in un repository git, non fare nulla.

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. 10d ago First seen · 62 lines · 10 tokens per session scan A 75908aff1ac5

Subscribe to this mod's changes

book-review is a command published in the GitHub repository fullo/claude-writing-assistant-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 805 once invoked, about $0.0001 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.