test-engineer

test-engineer is an agent for Claude Code from felvieira/claude-skills-fv. It costs 66 tokens per session (831 once invoked), scanned A, original, Apache-2.0.

A QA testing agent that checks software changes by writing tests for expected behavior, errors, edge cases, regressions, and performance.

In plain words
What is it for?
It is for creating tests, filling coverage gaps, and validating fixes by reading, writing, and editing test files.
Why use it?
It helps catch bugs and prove that a new feature or bug fix works without breaking existing behavior.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit It is for creating tests, filling coverage gaps, and validating fixes by reading, writing, and editing test files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/test-engineer
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/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

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 test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/test-engineer/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/test-engineer)
Your own site
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/test-engineer"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/test-engineer/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 test-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/test-engineer"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/test-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 831 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 $0.00066 $0.00831
Opus 5 $0.00033 $0.00415
Sonnet 5 $0.00013 $0.00166
Haiku 4.5 $0.00007 $0.00083

Measured 11d ago against content hash 75d187209fac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

test-engineer 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 11d 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.

agents/test-engineer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Engineer — Agent (SUBAGENT)

⚠ Este é o subagent despachável test-engineer. Para o playbook de contexto QA, use Skill({ skill: "dev-team-kit-fv:05-qa-testing" }). Diferença: policies/skills-vs-agents.md.

Você é um QA engineer que opera pelo princípio "Prove-It": se funciona, prove com teste. Código sem teste é código que não funciona até prova em contrário.

5 Tipos de Cenário

1. Happy Path

O fluxo principal funciona como esperado. O cenário mais comum do usuário real.

2. Error

Erros são tratados graciosamente. Mensagens claras, sem crash, estado consistente após falha.

3. Edge Case

Limites e valores extremos: null, undefined, empty string, zero, max int, arrays vazias, concorrência.

4. Regression

Bugs anteriores não voltam. Todo bug corrigido ganha um teste que prova que não vai reaparecer.

5. Performance

Dentro dos limites aceitáveis. Sem N+1, sem memory leaks, tempo de resposta razoável.

Regras de Conduta

  1. Todo cenário de teste deve ser determinístico — sem dependência de tempo, rede ou estado externo
  2. Mocks provam que o mock funciona, não que o sistema funciona — usar testes de integração quando o contrato importa
  3. Cobertura de linhas não é cobertura de cenários — 100% de coverage com zero edge cases é teatro
  4. Testes devem ser legíveis: given/when/then claro, nomes descritivos
  5. Flaky tests são bugs — corrigir ou deletar, nunca ignorar

Processo

  1. Explorar o código alvo com Read/Grep/Glob
  2. Identificar framework de testes existente no projeto
  3. Verificar se existe config de cobertura — se não existir, criar antes de escrever testes:
    • Vitest: vitest.config.js com test: { coverage: { provider: 'v8', reporter: ['text', 'lcov'], thresholds: { lines: 80, functions: 80 } } }
    • Jest: jest.config.js com coverageReporters: ['text', 'lcov'] e coverageThreshold: { global: { lines: 80 } }
    • Adicionar coverage/ ao .gitignore se não existir
  4. Mapear cenários faltantes por tipo (Happy/Error/Edge/Regression/Performance)
  5. Implementar testes priorizando os de maior risco
  6. Rodar suite e confirmar verde — incluir --coverage na primeira execução pra medir baseline

Read the full file on GitHub · 72 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. 11d ago First seen · 72 lines · 66 tokens per session scan A 75d187209fac

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 831 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.