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.
git 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-scaffold)<a href="https://agentmods.dev/commands/4pixeltechbr/vibedev/vd-scaffold"><img src="https://agentmods.dev/badge/commands/4pixeltechbr/vibedev/vd-scaffold/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/commands/4pixeltechbr/vibedev/vd-scaffold"><img src="https://agentmods.dev/badge/commands/4pixeltechbr/vibedev/vd-scaffold.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 | $0.00000 | $0.02107 |
| Opus 5.5 | $0.00000 | $0.00843 |
| Sonnet 5.5 | $0.00000 | $0.00421 |
| Haiku 4.5 | $0.00000 | $0.00211 |
Grade A, and why
vd-scaffold 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 15d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/vd-scaffold
Protocolo vigente está no
SKILL.md. Se este arquivo divergir,SKILL.mdvence.
Abra só quando o passo aprovado for fundação (schema, login, pagamento, vários clientes). Gere o componente desse passo, não os quatro. Stack já escrita no estado: use essa e não refaça a triagem. No mapa leigo, fundação cabe em "Decidir como construir", não numa "Fase 3 — Arquitetura".
🇧🇷 PT-BR · 🇺🇸 EN follows
Motor de Fundação Técnica do VibeDev. Roda dentro de
/vd-buildquando a sub-tarefa envolve fundação (banco, auth, pagamento, multi-tenant, white-label) na Fase 3 — Arquitetura da Trilha Verde.
🇧🇷 O que faz
Transforma a intenção já aprovada em /vd-plan em fundação técnica real:
schema + migrations, matriz RBAC, integração de pagamento BR-first com webhook
idempotente, e tokens de white-label. Não fixa stack — decide por contexto
via Triagem Cynefin-lite.
Princípio central: stack é decisão Tipo 1. Nunca escolhe por hábito nem aceita primeira opção sem Red Team. O código gerado tem que ser copy-paste funcional — declarar "estrutura pronta pra escala" sem entregar migration e índice reais é proibido aqui.
🇺🇸 What it does
Turns the intent already approved in /vd-plan into real technical foundation:
schema + migrations, RBAC matrix, BR-first payment integration with idempotent
webhook, and white-label tokens. Does not fix stack — decides by context
via Cynefin-lite triage.
Central principle: stack is Type 1 decision. Never chooses by habit nor accepts the first option without Red Team. Generated code must be copy-paste functional — declaring "structure ready to scale" without delivering real migration and index is forbidden here.
🚦 Quando ativar (gate)
Ativação automática quando TODAS as condições:
trilha: verdeemPROJECT_STATE.md- Fase atual = Fase 3 — Arquitetura (ou o usuário marcar explicitamente "fase de fundação")
- Sub-tarefa aprovada em
/vd-planenvolve QUALQUER destes:- Modelagem de dados (banco, schema)
- Autenticação / permissões
- Pagamentos / assinaturas
- Multi-tenancy
- White-label / identidade visual parametrizada
- Estrutura inicial de pastas do projeto
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.
- 15d ago Changed · +4 lines aaeb3afb7024
- 2mo ago First seen · 181 lines · 0 tokens per session scan A b98d088511db
vd-scaffold is a command published in the GitHub repository 4pixeltechBR/VibeDev (17 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,107 tokens. 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.
vd-scaffold compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vd-scaffold4pixeltechBR/VibeDev | Command | 17 | 16d ago | MIT | A | 0 | Claude Code |
| schema-reviewspree/spree | Command | 16k | yesterday | BSD-3-Clause | A | 0 | Claude Code |
| migratevendurehq/vendure | Command | 8.6k | yesterday | none | A | 0 | Claude Code |
| django-modelJustdvp/claude-code-templates | Command | 7 | 25d ago | MIT | A | 0 | Claude Code |
| databaseJustdvp/claude-code-templates | Command | 7 | 25d ago | MIT | A | 0 | Claude Code |
| auditofershap/drizzle-best-practices | Command | 0 | 8mo ago | MIT | A | 14 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |