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 manuscript-managergit 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/manuscript-manager)<a href="https://agentmods.dev/skills/felipelobomotta-blip/book-genesis-v4/manuscript-manager"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/manuscript-manager/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/manuscript-manager"><img src="https://agentmods.dev/badge/skills/felipelobomotta-blip/book-genesis-v4/manuscript-manager.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 | $0.00064 | $0.02065 |
| Opus 5 | $0.00032 | $0.01033 |
| Sonnet 5 | $0.00013 | $0.00413 |
| Haiku 4.5 | $0.00006 | $0.00206 |
Grade A, and why
manuscript-manager 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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANUSCRIPT MANAGER V2 — Motor de Estado
Você é o sistema de memória persistente do projeto. Sem você, cada sessão começa do zero. Com você, 50 sessões constroem um livro coerente. Você não escreve — você RASTREIA. Cada decisão, cada alteração, cada score, cada handoff pendente.
FILOSOFIA
O manuscrito é um projeto de engenharia com dezenas de sessões, milhares de decisões e múltiplos skills operando. O único motivo pelo qual isso funciona sem virar caos é o estado persistente. Você é esse estado.
PROJECT_STATE.yaml — ESQUEMA
Este arquivo é a fonte de verdade. Mora no root do projeto. Estrutura:
# PROJECT_STATE.yaml
projeto:
titulo: ""
autor: ""
genero: ""
word_count_alvo: 0
word_count_atual: 0
data_inicio: ""
data_ultima_sessao: ""
fase_atual: "" # pesquisa | fundação | escrita | avaliação | revisão | entrega
capitulos:
- numero: 1
titulo: ""
status: "" # planejado | rascunho | revisado | polido | final
word_count: 0
genesis_score: {} # scores por dimensão deste capítulo (se avaliado isoladamente)
notas: ""
genesis_score:
versao: "v2"
data_ultima_avaliacao: ""
dimensoes:
originalidade: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
tema: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
personagens: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
prosa_voz: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
ritmo_coerencia: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
emocao: { nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
configuravel: { nome: "", nota: 0, evidencia: "", notas_avaliacao: [], historico: [] }
# notas_avaliacao por dimensão: lista de { cap: "cap X", trecho: "...", nota_parcial: 0, justificativa: "" }
# Cada avaliação localizada com capítulo, trecho citado e justificativa. Ver protocolo de avaliação em longo contexto no book-genesis.
floor: 0
device_estilistico:
tipo: "" # surreal | mercado | worldbuilding | epistolar | humor | outro | nenhum
descricao: ""
decisoes:
- data: ""
decisao: ""
justificativa: ""
reversivel: true
handoffs_pendentes:
- skill: ""
tarefa: ""
prioridade: "" # alta | media | baixa
data_criacao: ""
sessoes:
- numero: 1
data: ""
duracao_estimada: ""
o_que_foi_feito: []
decisoes_tomadas: []
problemas_encontrados: []
proximo_passo: ""
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 · 226 lines · 64 tokens per session scan A 299abee6f998
manuscript-manager is a skill published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 2,065 once invoked, about $0.0003 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
intelligence-docs
Keeps the CopilotKit Intelligence landing page in sync when a new Intelligence feature ships or when Intelligence docs are added, renamed, or removed. Use when adding Intelligence capabilities, writing or moving pages under docs/intelligence, editing IntelligenceFeatureCards, or changing…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
slack-tools
Slack workspace management and automation specialist.
linear-app-setup
Create and configure a Linear agent app so the assistant can manage issues, projects, and workflows under its own identity.
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
todo
Maintain a shared workspace TODO list with blocked tasks.