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-help)<a href="https://agentmods.dev/commands/4pixeltechbr/vibedev/vd-help"><img src="https://agentmods.dev/badge/commands/4pixeltechbr/vibedev/vd-help/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-help"><img src="https://agentmods.dev/badge/commands/4pixeltechbr/vibedev/vd-help.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 | $0.00373 |
| Opus 5.5 | $0.00000 | $0.00149 |
| Sonnet 5.5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
vd-help 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 2d 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.
What it actually says
/vd-help
A pessoa chamou porque perdeu o fio. Responda com o próximo comando e pare. Não recite o framework.
SKILL.md vence se este arquivo divergir.
Próximo passo
| Situação | Comando |
|---|---|
Só uma ideia, ainda sem PROJECT_STATE.md |
Fatia (as 4 perguntas numa mensagem, depois a menor tela) |
| Já tem código e está quebrado | Resgate (3 perguntas, conserta só o desta semana) |
| Quer saber onde está | /vd-status |
| Quer decidir o próximo pedaço | /vd-plan |
| O plano já foi aceito | /vd-build |
| Quer saber se funcionou | /vd-check |
| Vai embora hoje | /vd-close |
| Quer parar o projeto | /vd-kill |
| Mapa leigo | 1 Entender o problema · 2 Decidir como construir · 3 Construir · 4 Testar · 5 Colocar no ar |
| Mapa técnico de 8 fases | Só se modo_usuario: tecnico. Abra references/trilha-verde.md |
/vd-arch-review é auditoria para quem já programa. Não ofereça no modo leigo.
Uma linha por comando
Fatia ideia → uma coisa visível
/vd-status onde estou
/vd-plan próximo pedaço, e para
/vd-build faz o plano inteiro
/vd-check aconteceu na tela agora?
/vd-launch depois que Testar passou
/vd-close salva e encerra a sessão
/vd-kill encerra o projeto e guarda o aprendizado
Se ela só for lembrar de um, é /vd-status.
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.
- 2d ago Changed · -82 lines fd1f90a852dd
- 1mo ago First seen · 120 lines · 0 tokens per session scan A 24acaf24848a
vd-help is a command published in the GitHub repository 4pixeltechBR/VibeDev (17 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 373 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.
Other commands, from other repositories
park
Park current session for later resume (append to Markdown file).
context
Manage workflow context (handoffs, todos, session status).
budget-mode
Activate cost-conscious behavior for the rest of this session.
release-notes
A release-notes generator that reads Git history and prepares a Keep a Changelog entry, a standard format for recording software changes, plus text for users.
sota-close
End-of-session closure pass — retract what proved wrong and correct it everywhere it reached, hand off open items where the next session will trip over them, update the docs this session made false, re-derive every number from its source, and commit the evidence. Run it at the END of a working session.
sota-report
Write a SOTA-skills field report for this session — where the guidance failed, was absent, was wrong, or was right and did not fire. Run it at the END of a working session, while the history is still in context.