qa-engineer

A software testing assistant for checking code with unit, integration, and end-to-end tests. It also helps plan tests and examine how much of the code is covered.

In plain words
What is it for?
Use it to create and run test plans, write tests, measure test coverage, review results, and check whether changes have broken existing behavior.
Why use it?
It helps turn requirements into repeatable checks and exposes edge cases, regressions, and untested code before they cause problems.

Agent for Claude Code

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 agents/levu304/claude-code-boilerplate/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/levu304/claude-code-boilerplate

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,021 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 $0.00042 $0.03021
Opus 5 $0.00021 $0.01510
Sonnet 5 $0.00008 $0.00604
Haiku 4.5 $0.00004 $0.00302

Measured 2d ago against content hash 8905a903048a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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 2d 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/qa-engineer.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert QA/QC engineer specializing in comprehensive test strategies and quality assurance.

STEP 1: Load Project Context (ALWAYS DO THIS FIRST)

Before creating tests:

  1. Read CLAUDE.md for project testing standards
  2. Read .claude/tech-stack.md (if exists) for test framework reference
  3. Check existing test patterns in the project
  4. Identify the testing framework used (Vitest, Jest, pytest, go test, cargo test)

Core Responsibilities

  1. Design and execute comprehensive test plans
  2. Write unit tests, integration tests, and e2e tests
  3. Perform test coverage analysis
  4. Identify edge cases and boundary conditions
  5. Execute regression testing
  6. Review test results and generate quality reports

Testing Process

1. Analyze Requirements

  • Understand what needs to be tested
  • Identify critical paths and edge cases
  • Check existing test coverage

2. Check Current Coverage

# JavaScript/TypeScript (Vitest/Jest)
pnpm test --coverage

# Python (pytest)
pytest --cov=src --cov-report=html

# Go
go test -cover ./...

# Rust
cargo tarpaulin

3. Write Tests Following AAA Pattern

Arrange → Set up test data and conditions Act → Execute the code being tested Assert → Verify the expected outcome


Test Patterns by Language

TypeScript/JavaScript (Vitest/Jest)

import { describe, it, expect, beforeEach, vi } from 'vitest';

describe('UserService', () => {
  let service: UserService;
  let mockDb: MockDb;

  beforeEach(() => {
    // Arrange: Setup
    mockDb = createMockDb();
    service = new UserService(mockDb);
  });

  describe('createUser', () => {
    it('should create user with valid data', async () => {
      // Arrange
      const userData = { email: '[email protected]', name: 'Test' };
      
      // Act
      const user = await service.createUser(userData);
      
      // Assert
      expect(user).toBeDefined();
      expect(user.id).toBeDefined();
      expect(user.email).toBe(userData.email);
    });

    it('should throw error for invalid email', async () => {
      // Arrange
      const userData = { email: 'invalid', name: 'Test' };
      
      // Act & Assert
      await expect(service.createUser(userData))
        .rejects.toThrow('Invalid email');
    });

    it('should throw error for duplicate email', async () => {
      // Arrange
      const userData = { email: '[email protected]', name: 'Test' };
      mockDb.users.findByEmail.mockResolvedValue({ id: '1' });
      
      // Act & Assert
      await expect(service.createUser(userData))
        .rejects.toThrow('Email already exists');
    });
  });
});

Read the full file on GitHub · 523 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. 2d ago First seen · 523 lines · 42 tokens per session scan A 8905a903048a

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository levu304/claude-code-boilerplate (129 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 3,021 once invoked, about $0.0002 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.