review

review is a command for Claude Code from lucasandradeb/my-claude-code-config. It costs 5 tokens per session (1,413 once invoked), scanned A, original, MIT.

A Portuguese-language checklist and style guide for reviewing a GitHub pull request, meaning a proposed set of code changes. It specifies checks for the pull request's status, contents, and existing reviews.

In plain words
What is it for?
Use it to inspect pull-request metadata and diffs, identify real bugs or suggestions, and write short, friendly feedback in Brazilian Portuguese.
Why use it?
It makes reviews more consistent and helps avoid spending time on closed, draft, automated, trivial, or already-reviewed changes.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to inspect pull-request metadata and diffs, identify real bugs or suggestions, and write short, friendly feedback in Brazilian Portuguese.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/lucasandradeb/my-claude-code-config/review
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.

Clone the repo
git clone --depth 1 https://github.com/lucasandradeb/my-claude-code-config

Made for: Claude Code.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/lucasandradeb/my-claude-code-config/review/github.svg)](https://agentmods.dev/commands/lucasandradeb/my-claude-code-config/review)
Your own site
<a href="https://agentmods.dev/commands/lucasandradeb/my-claude-code-config/review"><img src="https://agentmods.dev/badge/commands/lucasandradeb/my-claude-code-config/review/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/lucasandradeb/my-claude-code-config/review"><img src="https://agentmods.dev/badge/commands/lucasandradeb/my-claude-code-config/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00005 $0.01413
Opus 5 $0.00003 $0.00707
Sonnet 5 $0.00001 $0.00283
Haiku 4.5 $0.00001 $0.00141

Measured 9d ago against content hash 3bb98c2ed847, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

commands/review.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Faça uma code review completa do pull request indicado.

Estilo e Tom (OBRIGATÓRIO — seguir sempre)

  • Tom informal, didático e amigável — como um colega experiente dando feedback, não um robô
  • NUNCA use tom imperativo ("Faça isso", "Mude aquilo", "Corrija", "Adicione"). Use sempre: "seria legal...", "que tal...", "dá pra considerar...", "ficaria melhor se...", "uma ideia seria..."
  • Comentários curtos e diretos — sem textão, sem rodeios
  • Elogie genuinamente quando algo estiver bem feito, elegante ou bem pensado
  • Responda sempre em português brasileiro
  • Emojis com moderação — use apenas bug: para bugs reais e ideia: para sugestões. Sem decoração excessiva

Processo de Review

Siga os passos abaixo:

  1. Use um agente Haiku para verificar se o PR: (a) está fechado, (b) é draft, (c) é automatizado ou trivialmente ok, (d) já tem review sua. Se qualquer um for verdade, não continue.

  2. Use um agente Haiku para obter o "pacote de review" do PR. Este agente deve:

    • Buscar gh pr view {pr} --json title,body,files,headRefOid
    • Buscar gh pr diff {pr}
    • Filtrar o diff: remover blocos que são apenas mudanças de formatação/indentação ou imports mecânicos (ex: renomear namespace em massa). Manter apenas mudanças com lógica real.
    • Retornar: SHA do head commit, lista de arquivos funcionais modificados, e o diff filtrado completo.
  3. Lance 2 agentes Sonnet em paralelo, passando o diff filtrado do passo 2 diretamente no prompt (não buscar o diff de novo):

    • Agente A — Bugs e lógica: Analisa o diff filtrado em busca de bugs reais, erros de lógica, problemas de segurança, edge cases ignorados. Para cada issue: descrever o problema, indicar arquivo + linha exata no arquivo (não no diff), e dar um score de 0-100 de confiança.
    • Agente B — Qualidade e padrões: Analisa o diff filtrado em busca de problemas de qualidade que violem padrões explícitos do projeto (se houver CLAUDE.md), código comentado introduzido, TODOs deixados, inconsistências com o restante do PR. Para cada issue: descrever, arquivo + linha exata, score 0-100.

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 5 tokens per session scan A 3bb98c2ed847

Subscribe to this mod's changes

review is a command published in the GitHub repository lucasandradeb/my-claude-code-config (2 stars, last pushed 21d ago), licensed MIT. It adds 5 tokens to every session and 1,413 once invoked, about $0.0000 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.