What is verificar-trabalho?

A conversational user-acceptance testing command that checks whether a completed feature works from the user's perspective. UAT means testing real user scenarios rather than only checking internal code.

Use it to test one user scenario at a time, document pass or fail results, and prepare correction plans when problems are found.

It helps uncover problems that automated or developer-focused tests may miss and records the results in a UAT report.

verificar-trabalho — Command for Claude Code by luanpdd

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/luanpdd/kit-mcp

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/commands/luanpdd/kit-mcp/verificar-trabalho/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/verificar-trabalho)

Your own site

<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/verificar-trabalho"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/verificar-trabalho/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/commands/luanpdd/kit-mcp/verificar-trabalho"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/verificar-trabalho.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 686 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	$0.00016	$0.00686
Opus 5	$0.00008	$0.00343
Sonnet 5	$0.00003	$0.00137
Haiku 4.5	$0.00002	$0.00069

Measured 5d ago against content hash 5f2c6704691f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verificar-trabalho 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 5d 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.

kit/commands/verificar-trabalho.md · 65 lines

What it actually says

Propósito: Confirmar que o que o Claude construiu realmente funciona da perspectiva do usuário. Um teste por vez, respostas em texto simples, sem interrogatório. Quando problemas são encontrados, automaticamente diagnostica, planeja correções e prepara para execução.

Saída: {phase_num}-UAT.md rastreando todos os resultados de teste. Se problemas encontrados: lacunas diagnosticadas, planos de correção verificados prontos para /executar-fase

<execution_context> @./.claude/framework/workflows/verify-work.md @./.claude/framework/templates/UAT.md </execution_context>

Arquivos de contexto são resolvidos dentro do workflow (init verify-work) e delegados via blocos <files_to_read>.

<observability_integration> Integração com Core Analysis Loop em logs reais (v1.9):

Quando workflow.observability_uat_validation = true (default) e o projeto tem MCP Supabase disponível, o workflow inclui passo de validação observacional após UAT conversacional:

Para cada test passing no UAT, invocar o agente incident-investigator em modo "validation":

Task(subagent_type="incident-investigator", prompt="
  mode: validation
  symptom: validar que feature de Phase {N} efetivamente emitiu spans/eventos esperados
  time_window: última 1h
  expected_attributes: {result.success: true, build_id: {current_build}}
")

O agente queryará via mcp__supabase__get_logs ou mcp__supabase__execute_sql para confirmar:
- Spans com nome esperado existem
- Atributos canônicos foram emitidos (não só código existe — comportamento real)
- result.success baseline está dentro do esperado
Se confirmado: UAT.md inclui evidência observacional (não só "funciona em UI"). Status passed ✓.
Se ausente: UAT.md flag human_needed com sugestão "verificar instrumentação não está pegando".

Skill consultada: core-analysis-loop — para o caso de UAT falhar e precisar investigar.

REQ: INT-FW-03. </observability_integration>

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.

5d ago First seen · 65 lines · 16 tokens per session scan A 5f2c6704691f

Subscribe to this mod's changes

verificar-trabalho is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 686 once invoked, about $0.0001 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 2026-09-03.

E2E testing Testing mcp

verificar-trabalho

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

paul:verify

webapp-testing

ui-snapshot.template

laravel-playwright

qa

verify-pr