vibeshield-code-review

A manually requested code-review command that checks a complete feature against project conventions and its written requirements. A pull request, or PR, is a proposed set of code changes for review.

In plain words
What is it for?
Use it to review a feature or PR for naming, folders, comments, errors, logs, tests, dependencies, and completion of the stated requirements.
Why use it?
It separates style and project-practice problems from failures to meet the feature specification. This can reveal issues that a review of the raw code difference alone may miss.

Command

Install

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.

agentmods
npx agentmods add commands/4pixeltechbr/vibedev/code-review
Clone the repo
git clone --depth 1 https://github.com/4pixeltechBR/VibeDev
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.01525
Opus 5 $0.00026 $0.00763
Sonnet 5 $0.00011 $0.00305
Haiku 4.5 $0.00005 $0.00153

Measured yesterday against content hash 3c8038eab5af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibeshield-code-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 yesterday.

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.

vibeshield/commands/code-review.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review — VibeShield

Skill dedicada de revisão de código/PR dentro do ciclo VibeDev. Diferente da auditoria gatilho (G1-G7) que dispara em sub-tarefas de risco: code-review é chamada pelo humano quando quer revisar o diff inteiro de uma feature.

Inspirado em code-review de mattpocock/skills (referência competitiva), mas com adaptação pro contexto VibeDev: a revisão é feita contra o estado do projeto (não só contra diff cru), e respeita modo leigo/técnico.

Tipo de invocação

User-invoked. Só humano chama. Modelo nunca dispara sozinho. Decisão humana, não automatizável.

Os 2 eixos

Toda review gera achados em uma (ou ambas) destas categorias:

Eixo 1: Standards

"Esse código segue convenções que a VibeDev esperaria?"

  • Naming consistente com o resto do projeto?
  • Estrutura de pastas alinhada com decisões do PROJECT_STATE.md?
  • Comentários onde precisa (não onde não precisa)?
  • Tratamento de erro uniforme?
  • Logs no padrão do projeto?
  • Testes no padrão definido?
  • Dependências justificadas?

Eixo 2: Spec

"Esse código faz o que a spec (sub-tarefa ativa) diz que deveria fazer?"

  • Critério de "pronto" da sub-tarefa tá atendido?
  • Casos listados na spec foram cobertos?
  • Casos não-listados (anti-escopo) foram respeitados?
  • Decisões Tipo 1 do plano foram seguidas?
  • Outputs do código batem com outputs esperados?

Como rodar

Inputs necessários

  • PROJECT_STATE.md (carregado automaticamente pela skill)
  • Diff ou PR (pode ser colado, ou apontar pra branch/commit)
  • Identificação da sub-tarefa ativa (lê do estado)

Fluxo

  1. Confirma inputs com o usuário: "Vou revisar o diff X contra a sub-tarefa Y do estado. Certo?"
  2. Coleta diff: lê arquivos modificados, prepara contexto
  3. Análise Eixo 1 (Standards): percorre convenções do projeto
  4. Análise Eixo 2 (Spec): compara com critério de pronto da sub-tarefa
  5. Compila achados: lista unificada, ordenada por severidade
  6. Devolve veredito:
    • OK (sem achados, ou só nits) — pode commitar
    • REVISAR (amarelos) — commita mas anota no backlog
    • BLOQUEAR (vermelhos) — não commita, voltar pra /vd-build

Read the full file on GitHub · 144 lines

Changes

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.

  1. yesterday First seen · 144 lines · 0 tokens per session scan A 3c8038eab5af

Subscribe to this mod's changes

vibeshield-code-review is a command published in the GitHub repository 4pixeltechBR/VibeDev (16 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,525 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 2026-08-30.