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.
/plugin marketplace add fullo/claude-writing-assistant-skill/plugin install writing-assistantWrote 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.
[](https://agentmods.dev/commands/fullo/claude-writing-assistant-skill/book-markua)<a href="https://agentmods.dev/commands/fullo/claude-writing-assistant-skill/book-markua"><img src="https://agentmods.dev/badge/commands/fullo/claude-writing-assistant-skill/book-markua/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.
<a href="https://agentmods.dev/commands/fullo/claude-writing-assistant-skill/book-markua"><img src="https://agentmods.dev/badge/commands/fullo/claude-writing-assistant-skill/book-markua.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00014 | $0.00870 |
| Opus 5 | $0.00007 | $0.00435 |
| Sonnet 5 | $0.00003 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
book-markua 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.
What it actually says
Valida il formato Markua del file o della directory indicata in $ARGUMENTS.
Prerequisito piattaforma: leggere book-config.md nella root del progetto. Se il campo Piattaforma è diverso da LeanPub (Markua), informare l'utente: "Questo comando è specifico per il formato Markua/LeanPub. Il progetto usa [piattaforma]. Le regole Markua non si applicano." Se book-config.md non esiste o non specifica la piattaforma, procedere con la validazione Markua (default).
Prima leggere: ${CLAUDE_PLUGIN_ROOT}/skills/markua-leanpub/SKILL.md e ${CLAUDE_PLUGIN_ROOT}/skills/markua-leanpub/references/markua-rules.md.
Se $ARGUMENTS è un singolo file .md, validare quel file.
Se $ARGUMENTS è una directory di progetto libro o non specificato, cercare book.txt in capitoli/ (o nella directory corrente), leggere l'elenco dei capitoli e validarli tutti.
Struttura attesa: nome-libro/capitoli/book.txt + file .md nella stessa directory.
Per ogni file, controllare:
- Titolo — H1 unico con formato
# Capitolo N: Titolo — Sottotitolo - Epigrafe — virgolette senza corsivo, attribuzione su singola riga con
— **Autore** - Separatore —
---presente dopo epigrafe - Sezioni —
## N.M Titolo — Sottotitolocon trattino lungo (—), mai corto (-) - Pagebreak —
{pagebreak}prima di ogni##(tranne la prima) - Callout T> — label ammesse:
**Insight**,**Regola pratica**,**Approfondimento**. No emoji, no sottotitoli nella label - Callout W> — label
**Red Flag**con F maiuscola. No varianti - Callout Q> — label
**Domanda Socratica**senza emoji - Quick Win — in
{blurb, icon: trophy}, label bold (non H2), chiuso con{/blurb} - Checkpoint —
## Checkpoint capitolo N, sotto-sezioni###con ≥3 checkbox - Fine Parte —
## Fine Parte N — Nome(H2, non bold) - Emoji — zero emoji in callout, titoli, label
- Sentence case — tutti i titoli
- Tabelle — formato Markdown standard con allineamento
Output per ogni file:
FILE: nome-file.md
✅ Titolo: conforme
❌ Epigrafe: corsivo presente, rimuovere *"..."*
⚠️ Pagebreak: mancante prima di ## 3.4
...
RIEPILOGO: X errori, Y avvertimenti su Z file analizzati
Se si tratta di validazione multi-file, compilare anche la matrice di distribuzione callout (come in references/markua-rules.md).
Git commit
Se sono stati applicati fix al formato 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-markua: fix [N] errori formato in [file/i modificati]"
Se non ci si trova in un repository git o non sono stati applicati fix (solo analisi), non fare nulla.
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.
- 9d ago First seen · 58 lines · 14 tokens per session scan A f7d4651a9793
book-markua is a command published in the GitHub repository fullo/claude-writing-assistant-skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 870 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.