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.
npx skills add felipelobomotta-blip/book-genesis-v4 --skill prose-craftgit clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4Wrote 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/skills/felipelobomotta-blip/book-genesis-v4/prose-craft)<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/prose-craft"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/prose-craft/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/skills/felipelobomotta-blip/book-genesis-v4/prose-craft"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/prose-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.04385 |
| Opus 5 | $0.00040 | $0.02193 |
| Sonnet 5 | $0.00016 | $0.00877 |
| Haiku 4.5 | $0.00008 | $0.00439 |
Grade A, and why
prose-craft 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROSE CRAFT — Abertura + Diálogo + Qualidade de Linha
Você opera no nível da frase. Enquanto outros skills cuidam de estrutura, personagem e tema, você cuida de como cada linha SOA. Uma ideia brilhante executada com prosa medíocre é um livro que ninguém termina. Prosa é a interface entre o escritor e o leitor — se a interface é ruim, o conteúdo não importa.
PARTE 1 — ABERTURA (5 CAMADAS DE GANCHO)
A abertura decide tudo. Editor lê a primeira página e decide se continua. Leitor abre o ebook, lê o sample de 10% e decide se compra. As primeiras palavras carregam mais peso que qualquer outra parte do livro.
Camada 1: Primeira Linha
A primeira frase deve fazer UMA coisa: impedir o leitor de parar.
4 tipos que funcionam:
Tipo A — Conflito imediato:
"Eu fumei um baseado numa praia chamada Sossego e nunca mais tive sossego." Situação + consequência em uma frase. O leitor quer saber o que aconteceu.
Tipo B — Voz irresistível:
"Minha mãe me ligou às seis da manhã pra dizer que eu parecia triste no Instagram." O tom é tão específico que o leitor segue pela voz, não pela trama.
Tipo C — Informação retida:
"Três coisas que ninguém te conta sobre eletroconvulsoterapia." Promessa de revelação. O leitor precisa saber quais são.
Tipo D — Imagem inesquecível:
"O consultório do psiquiatra tinha um quadro de girassóis na parede. Custava R$ 400 a hora. Os girassóis eram de graça." Imagem tão vívida e inesperada que gruda.
Camada 2: Primeiro Parágrafo
Estabelece voz e tom. O leitor sabe, em 3-4 frases, que tipo de livro está lendo.
- Parágrafo longo e lírico = livro contemplativo
- Parágrafos curtos e secos = livro direto
- Mistura de registro = livro que surpreende
Camada 3: Primeira Página
Cria compromisso. Ao final da primeira página, o leitor deve ter:
- Uma pergunta que quer respondida
- Um personagem sobre quem quer saber mais
- Uma sensação do tom que vai encontrar
Camada 4: Primeira Cena
Entrega a promessa do gênero. Se é memoir de saúde mental, o leitor deve sentir a vulnerabilidade. Se é thriller, deve sentir perigo. Se é humor, deve ter rido.
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.
- 12d ago First seen · 306 lines · 80 tokens per session scan A 530139429166
prose-craft is a skill 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 4,385 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 2026-08-30.
Other skills, from other repositories
humanizer
Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when…
clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…
voiceprint
Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words…
monograph-writing
A workflow for managing the writing of long books, textbooks, academic monographs, technical books, or dissertations in small, checkable batches.
red-pen
A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…
slop-detector
Score a draft, page, or caption set for AI slop with a four-tier severity model instead of a flat banned-words list. Exact production narration fails outright, rhetorical scaffolds warn only when repeated, lexical tells become review prompts, and document-level patterns are diagnosed. Use when the user asks to score…