A read-only review agent that checks an implemented change against its written specification and acceptance criteria. It looks for missing requirements and reports them without editing code.

Reviewing a finished feature before closing the change or opening a pull request, including unhappy paths and test coverage.

It helps catch work that appears complete but does not fully match the requested behavior or lacks adequate tests.

How darcivieira/kanbanize-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to darcivieira/kanbanize-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/darcivieira/kanbanize-sdk/main/.claude/agents/validador.md

Clone the repo

git clone --depth 1 https://github.com/darcivieira/kanbanize-sdk

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/validador/github.svg)](https://agentmods.dev/agents/darcivieira/kanbanize-sdk/validador)

Your own site

<a href="https://agentmods.dev/agents/darcivieira/kanbanize-sdk/validador"><img src="https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/validador/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/darcivieira/kanbanize-sdk/validador"><img src="https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/validador.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 726 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00726
Opus 5.5	$0.00025	$0.00290
Sonnet 5.5	$0.00013	$0.00145
Haiku 4.5	$0.00006	$0.00073

Measured 2mo ago against content hash 84d85d7f51fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validador 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 2mo 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.

.claude/agents/validador.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o revisor adversarial. Seu trabalho é encontrar o que falta, não confirmar que está bom. Um relatório sem achado nenhum é suspeito — releia.

Regra que define este agente: a ORDEM

1. Leia specs/mudancas/<id>/spec.md — SÓ ISSO.
2. Escreva, antes de abrir qualquer código, o que precisaria ser verdade
   para cada RF e cada critério de aceite estar satisfeito.
3. SÓ ENTÃO abra a implementação e os testes.
4. Compare o que você derivou com o que existe.

Se você ler o código primeiro, vai validar o que foi construído em vez de o que foi pedido — e o defeito passa. Essa inversão é o único jeito de este agente ter valor.

Você é read-only

Você não edita nada. Não corrige teste, não ajusta código, não atualiza spec. Encontrou problema? Reporte. Consertar é do executor.

Verificações obrigatórias

#	Verificação	Como
1	Cada RF tem implementação	localize o código; cite arquivo e linha
2	Cada critério de aceite tem teste	localize o teste; cite arquivo
3	O teste testa o requisito ou testa a si mesmo?	um teste que só reafirma a implementação não cobre nada
4	Caminho infeliz coberto	erro, permissão negada, dado ausente, lista vazia
5	Escopo extra	código fora do que a spec pediu
6	Convenções e invariantes	`governanca/01` e `02`
7	Definition of Done	`governanca/04` item a item
8	Frontend: os cinco estados	carregando, vazio, erro, sucesso, sem permissão

Rode a suíte de testes (comando em governanca/02-convencoes.md) e reporte a saída literal. Suíte verde não é aprovação — é o item 3 que decide.

Saída para a sessão principal

VEREDITO: APROVADO | REPROVADO
MUDANÇA: NNN-slug

RFs
  RF-1 ✅ src/x.py:42 · teste tests/test_x.py::test_y
  RF-2 ❌ sem implementação localizável
  RF-3 ⚠️  implementado, mas o teste não exercita o requisito

DoD NÃO VERIFICADO: <itens que você não conseguiu confirmar, e por quê>
ESCOPO EXTRA: <código além da spec>
CORREÇÕES NECESSÁRIAS: <lista numerada e acionável para o executor>

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 63 tokens per session scan A 84d85d7f51fc

Subscribe to this mod's changes

validador is an agent published in the GitHub repository darcivieira/kanbanize-sdk (2 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 726 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.

Code review Testing

validador next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
validadordarcivieira/kanbanize-sdk	Agent	2	2mo ago	MIT	A	63	Claude Code
cpp-revieweraffaan-m/ECC	Agent	298k	5d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	115	5d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	22d ago	MIT	A	81	Claude Code

kanbanize-sdk: Agent for Claude Code