Borrowing it
Nothing to install: this file belongs to gabrielzucco/cerebro-inevita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/comecar/SKILL.mdgit clone --depth 1 https://github.com/gabrielzucco/cerebro-inevitaWrote 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/gabrielzucco/cerebro-inevita/comecar)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/comecar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/comecar/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/gabrielzucco/cerebro-inevita/comecar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/comecar.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 | $0.00054 | $0.03045 |
| Opus 5.5 | $0.00022 | $0.01218 |
| Sonnet 5.5 | $0.00011 | $0.00609 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade A, and why
comecar 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 20d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Começar — configurar o cérebro com realidade, não com formulário
A pasta local é o cérebro. Manus, Codex, Claude, Gemini ou qualquer outra IA baseada em arquivos é apenas o operador atual. A primeira sessão deve deixar contexto durável na pasta e um resultado que a pessoa possa usar — não apenas respostas numa conversa.
Primeiro confirme a casa e recupere o trabalho pelo passo 1. Depois, na instalação escolhida,
leia .cerebro/layout.json, sistemas/cerebro-base/manifest.md, pipeline.md e evals.md. No
layout, prefira activationBrief, configuration e activationContract; aceite os aliases legados
firstSystemBrief, contextPack e systemContract. Execute company-brain-sprint uma vez, no
passo 4, reaproveitando o que já foi apurado. Continue na conversa atual quando o agente conseguir
ler e escrever na pasta; não peça reinício nem troca de ferramenta por conveniência.
Experiência de abertura
- Use sempre
você,seuesuae reutilize o vocabulário da pessoa. - Faça uma pergunta por mensagem. Se a resposta já está no pedido ou nos arquivos autorizados, não pergunte de novo.
- Reutilize escolhas e autorizações explícitas da sessão dentro do escopo aprovado. Mostre a prévia concreta de uma mutação quando ainda faltar, sem repetir decisões já tomadas.
- Não abra com e-mail, menu, arquitetura, lista de ferramentas ou “o que você faz?”. O vínculo de acesso é oferecido somente depois do primeiro output útil e nunca bloqueia a ativação.
- Não exponha run-id, relógio, telemetria, A0/A1/A2, T0–T4 ou nomes internos do método.
- Não procure Node, rode
which node, altere PATH ou instale dependências para helpers opcionais. - Telemetria nunca é pedágio. Somente depois do output útil, rode seus helpers silenciosos e ignore qualquer falha sem interromper a pessoa. Uma verificação necessária à implantação autorizada pode usar o runtime já disponível; não é motivo para instalar dependências ou interromper valor.
1. Confirmar a casa e recuperar a operação
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed · +57 lines · +54 tokens per session fb88dc448b7c
- 1mo ago Changed · -5 lines d80be4faa015
- 1mo ago First seen · 141 lines · 0 tokens per session scan A 3988f95cf2c9
comecar is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (7 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 3,045 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.