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/arquiteto/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/arquiteto)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/arquiteto"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/arquiteto/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/arquiteto"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/arquiteto.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 | $0.00062 | $0.01710 |
| Opus 5 | $0.00031 | $0.00855 |
| Sonnet 5 | $0.00012 | $0.00342 |
| Haiku 4.5 | $0.00006 | $0.00171 |
Grade A, and why
arquiteto 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arquiteto — da operação ao primeiro sistema
Orquestre capacidades existentes. Não invente outro onboarding, outra régua de fontes ou outro runtime. O diagnóstico organiza o que foi declarado, aproxima a menor evidência útil, apresenta uma recomendação como proposta e deixa a pessoa decidir.
Contrato
- Entregue clareza sem inflar certeza. Mostre sempre o estado V0, V1, V2 ou V3.
- V0→V3 mede evidência do mapa; T0→T4 mede ativação do Cérebro Base. Nunca use uma escala para promover a outra.
- Reutilize
/prototipar,/fontee/operar; não replique esses protocolos. - Ranqueie no máximo três oportunidades, sem score numérico ou pesos não calibrados.
- Toda oportunidade leva
reason_codes, explicação e referências. - Ranking e primeiro sistema são propostas até o responsável confirmar.
- Não leia fonte sem autorização, não copie um acervo inteiro e não prometa conector inexistente.
- Não grave mapa derivado antes de mostrar o rascunho e receber aprovação.
- O arquivo canônico é
architect-spec.json; o visual é sempre derivado por engine.
1. Retomar o que já existe
Leia primeiro, quando existirem:
meu-negocio/mapa.md,oferta.md,icp.md,entrega.mdeo-que-funciona.md;- o recibo de ativação e o último marco T0→T4 do Cérebro Base;
- o fio quente em
meu-negocio/fios/; conexoes/configuradas/fontes.json, sem abrir as fontes;sistemas/_CATALOGO.mdesistemas/outros-instalados/_CATALOGO.md.
Não faça a pessoa repetir o que o Cérebro já sabe. Se T4 existe, prossiga para o primeiro Sistema
de negócio. Se a pessoa invocou esta skill diretamente antes de T4, prossiga com o diagnóstico e a
proposta, mas marque a recomendação como proposed e ofereça /comecar como o único próximo passo
para provar usar → reutilizar. O gate protege a implantação; não bloqueia clareza.
2. Construir V0 — declarado
Se o protótipo comercial, o protótipo de entrega, a frente e o loop ainda não estiverem claros,
execute /prototipar. Se já estiverem, reutilize-os.
What ships with it
4 files 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.
- 12d ago First seen · 167 lines · 62 tokens per session scan A a8811b0c6148
arquiteto is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 9d ago), licensed MIT. It adds 62 tokens to every session and 1,710 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 2026-08-31.
Other skills, from other repositories
handoff
Guides the Claude Code agent through completing a task, selecting a handoff tier, building a valid completion-card, and performing a clean task handoff.
x-harness-admission
Teach the x-harness admission workflow and completion-card discipline.
recovery
Handle blocked verification outcomes.
check-docs
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
deep-test
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.