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 agentmods add commands/4pixeltechbr/vibedev/vd-arch-reviewgit clone --depth 1 https://github.com/4pixeltechBR/VibeDevWrote 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/4pixeltechbr/vibedev/vd-arch-review)<a href="https://agentmods.dev/commands/4pixeltechbr/vibedev/vd-arch-review"><img src="https://agentmods.dev/badge/commands/4pixeltechbr/vibedev/vd-arch-review.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.02380 |
| Opus 5 | $0.00053 | $0.01190 |
| Sonnet 5 | $0.00021 | $0.00476 |
| Haiku 4.5 | $0.00011 | $0.00238 |
Grade A, and why
vd-arch-review 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 6d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vd-arch-review
Skill satélite de auditoria arquitetural. 3ª skill da família VibeDev (depois de VibeDev e VibeShield). User-invoked, sob demanda, focada em público dev (não leigo).
Inspirado em
improve-codebase-architecturede mattpocock/skills (referência competitiva) e na escada de 5 níveis de verificação de Sandeco Macedo (arXiv:2607.00038), adaptada pra VibeDev.
Tipo de invocação
User-invoked. Só humano chama. Modelo nunca dispara sozinho.
Por quê: auditoria arquitetural é decisão humana, não automatizável. Dev escolhe quando rodar, em qual escopo.
3 sub-comandos
| Comando | Níveis | Escopo | Quando usar |
|---|---|---|---|
/vd-arch-full |
1 + 2 + 3 | Stack + Arquitetura + Saúde | Onboarding em código legado, decisão de "vale a pena modernizar" |
/vd-arch-only |
2 | Arquitetura + Componentes | Adicionar módulo novo, ver onde plugar |
/vd-arch-health |
3 | Saúde + Débito Técnico | Antes de PR grande, antes de release, auditar qualidade |
Os 3 níveis (baseado em Sandeco, adaptado)
Nível 1 — Macro (Stack/Topologia)
Escopo: inventário de superfície.
- Linguagens usadas (TS, Python, Go, etc)
- Frameworks principais (Next.js, Django, etc)
- Banco de dados e ORM
- Sistema de build / package manager
- Contêineres / orquestração
- Dependências externas (diret vs transitivas)
- Estrutura de pastas de alto nível
Saída: lista de inventário + diagrama Mermaid de containers.
Nível 2 — Meso (Arquitetura/Fluxo)
Escopo: como o código se organiza.
- Módulos / bounded contexts
- Limites de responsabilidade (quem chama quem)
- Modelo de dados (entidades + relações)
- Rotas de API (REST, GraphQL, RPC)
- Fluxos críticos (login, pagamento, etc) em diagramas de sequência
Saída: diagrama de componentes Mermaid + diagrama de sequência dos fluxos principais.
Vocabulário (de mattpocock/skills codebase-design):
- Módulo — qualquer coisa com interface e implementação
- Seam — lugar onde você pode mudar comportamento sem editar ali
- Adapter — coisa concreta que satisfaz interface numa seam
- Deep vs Shallow — leverage na interface (muito comportamento por pouca interface)
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.
- 6d ago First seen · 209 lines · 105 tokens per session scan A 35ab3d453abb
vd-arch-review is a command published in the GitHub repository 4pixeltechBR/VibeDev (16 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 2,380 once invoked, about $0.0005 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 commands, from other repositories
implement
Execute phased implementation with validation gates.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
sync-linear
Sync current work with Linear ticket status.