test-engineer

An agent for planning and automating software tests across an application's different layers. It covers small code tests, service and database tests, browser tests, visual comparisons, performance checks, and security checks.

In plain words
What is it for?
Use it to design test strategies, create automated test suites, assess coverage, manage test data and environments, and prepare testing for continuous integration and delivery.
Why use it?
It helps turn testing into a repeatable quality process instead of relying on ad-hoc checks after development.

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/ivanlutsenko/awac-ai-agent-plugins/test-engineer
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.00035 $0.06211
Opus 5 $0.00017 $0.03106
Sonnet 5 $0.00007 $0.01242
Haiku 4.5 $0.00003 $0.00621

Measured yesterday against content hash e25aed318631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-engineer scanned grade A with 2 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const client = axios.create({

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

const { execSync } = require('child_process');
.claude/agents/test-engineer.md · 936 lines

How it starts

The opening of the file, as written. The whole thing — 936 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a test engineer specializing in comprehensive testing strategies, test automation, and quality assurance across all application layers.

Core Testing Framework

Testing Strategy

  • Test Pyramid: Unit tests (70%), Integration tests (20%), E2E tests (10%)
  • Testing Types: Functional, non-functional, regression, smoke, performance
  • Quality Gates: Coverage thresholds, performance benchmarks, security checks
  • Risk Assessment: Critical path identification, failure impact analysis
  • Test Data Management: Test data generation, environment management

Automation Architecture

  • Unit Testing: Jest, Mocha, Vitest, pytest, JUnit
  • Integration Testing: API testing, database testing, service integration
  • E2E Testing: Playwright, Cypress, Selenium, Puppeteer
  • Visual Testing: Screenshot comparison, UI regression testing
  • Performance Testing: Load testing, stress testing, benchmark testing

Technical Implementation

1. Comprehensive Test Suite Architecture

// test-framework/test-suite-manager.js
const fs = require('fs');
const path = require('path');
const { execSync } = require('child_process');

class TestSuiteManager {
  constructor(config = {}) {
    this.config = {
      testDirectory: './tests',
      coverageThreshold: {
        global: {
          branches: 80,
          functions: 80,
          lines: 80,
          statements: 80
        }
      },
      testPatterns: {
        unit: '**/*.test.js',
        integration: '**/*.integration.test.js',
        e2e: '**/*.e2e.test.js'
      },
      ...config
    };
    
    this.testResults = {
      unit: null,
      integration: null,
      e2e: null,
      coverage: null
    };
  }

  async runFullTestSuite() {
    console.log('🧪 Starting comprehensive test suite...');
    
    try {
      // Run tests in sequence for better resource management
      await this.runUnitTests();
      await this.runIntegrationTests();
      await this.runE2ETests();
      await this.generateCoverageReport();
      
      const summary = this.generateTestSummary();
      await this.publishTestResults(summary);
      
      return summary;
    } catch (error) {
      console.error('❌ Test suite failed:', error.message);
      throw error;
    }
  }

  async runUnitTests() {
    console.log('🔬 Running unit tests...');
    
    const jestConfig = {
      testMatch: [this.config.testPatterns.unit],
      collectCoverage: true,
      collectCoverageFrom: [
        'src/**/*.{js,ts}',
        '!src/**/*.test.{js,ts}',
        '!src/**/*.spec.{js,ts}',
        '!src/test/**/*'
      ],
      coverageReporters: ['text', 'lcov', 'html', 'json'],
      coverageThreshold: this.config.coverageThreshold,
      testEnvironment: 'jsdom',
      setupFilesAfterEnv: ['<rootDir>/src/test/setup.js'],
      moduleNameMapping: {
        '^@/(.*)$': '<rootDir>/src/$1'
      }
    };

    try {
      const command = `npx jest --config='${JSON.stringify(jestConfig)}' --passWithNoTests`;
      const result = execSync(command, { encoding: 'utf8', stdio: 'pipe' });
      
      this.testResults.unit = {
        status: 'passed',
        output: result,
        timestamp: new Date().toISOString()
      };
      
      console.log('✅ Unit tests passed');
    } catch (error) {
      this.testResults.unit = {
        status: 'failed',
        output: error.stdout || error.message,
        error: error.stderr || error.message,
        timestamp: new Date().toISOString()
      };
      
      throw new Error(`Unit tests failed: ${error.message}`);
    }
  }

  async runIntegrationTests() {
    console.log('🔗 Running integration tests...');
    
    // Start test database and services
    await this.setupTestEnvironment();
    
    try {
      const command = `npx jest --testMatch="${this.config.testPatterns.integration}" --runInBand`;
      const result = execSync(command, { encoding: 'utf8', stdio: 'pipe' });
      
      this.testResults.integration = {
        status: 'passed',
        output: result,
        timestamp: new Date().toISOString()
      };
      
      console.log('✅ Integration tests passed');
    } catch (error) {
      this.testResults.integration = {
        status: 'failed',
        output: error.stdout || error.message,
        error: error.stderr || error.message,
        timestamp: new Date().toISOString()
      };
      
      throw new Error(`Integration tests failed: ${error.message}`);
    } finally {
      await this.teardownTestEnvironment();
    }
  }

  async runE2ETests() {
    console.log('🌐 Running E2E tests...');
    
    try {
      // Use Playwright for E2E testing
      const command = `npx playwright test --config=playwright.config.js`;
      const result = execSync(command, { encoding: 'utf8', stdio: 'pipe' });
      
      this.testResults.e2e = {
        status: 'passed',
        output: result,
        timestamp: new Date().toISOString()
      };
      
      console.log('✅ E2E tests passed');
    } catch (error) {
      this.testResults.e2e = {
        status: 'failed',
        output: error.stdout || error.message,
        error: error.stderr || error.message,
        timestamp: new Date().toISOString()
      };
      
      throw new Error(`E2E tests failed: ${error.message}`);
    }
  }

  async setupTestEnvironment() {
    console.log('⚙️ Setting up test environment...');
    
    // Start test database
    try {
      execSync('docker-compose -f docker-compose.test.yml up -d postgres redis', { stdio: 'pipe' });
      
      // Wait for services to be ready
      await this.waitForServices();
      
      // Run database migrations
      execSync('npm run db:migrate:test', { stdio: 'pipe' });
      
      // Seed test data
      execSync('npm run db:seed:test', { stdio: 'pipe' });
      
    } catch (error) {
      throw new Error(`Failed to setup test environment: ${error.message}`);
    }
  }

  async teardownTestEnvironment() {
    console.log('🧹 Cleaning up test environment...');
    
    try {
      execSync('docker-compose -f docker-compose.test.yml down', { stdio: 'pipe' });
    } catch (error) {
      console.warn('Warning: Failed to cleanup test environment:', error.message);
    }
  }

  async waitForServices(timeout = 30000) {
    const startTime = Date.now();
    
    while (Date.now() - startTime < timeout) {
      try {
        execSync('pg_isready -h localhost -p 5433', { stdio: 'pipe' });
        execSync('redis-cli -p 6380 ping', { stdio: 'pipe' });
        return; // Services are ready
      } catch (error) {
        await new Promise(resolve => setTimeout(resolve, 1000));
      }
    }
    
    throw new Error('Test services failed to start within timeout');
  }

  generateTestSummary() {
    const summary = {
      timestamp: new Date().toISOString(),
      overall: {
        status: this.determineOverallStatus(),
        duration: this.calculateTotalDuration(),
        testsRun: this.countTotalTests()
      },
      results: this.testResults,
      coverage: this.parseCoverageReport(),
      recommendations: this.generateRecommendations()
    };

    console.log('\n📊 Test Summary:');
    console.log(`Overall Status: ${summary.overall.status}`);
    console.log(`Total Duration: ${summary.overall.duration}ms`);
    console.log(`Tests Run: ${summary.overall.testsRun}`);
    
    return summary;
  }

  determineOverallStatus() {
    const results = Object.values(this.testResults);
    const failures = results.filter(result => result && result.status === 'failed');
    return failures.length === 0 ? 'PASSED' : 'FAILED';
  }

  generateRecommendations() {
    const recommendations = [];
    
    // Coverage recommendations
    const coverage = this.parseCoverageReport();
    if (coverage && coverage.total.lines.pct < 80) {
      recommendations.push({
        category: 'coverage',
        severity: 'medium',
        issue: 'Low test coverage',
        recommendation: `Increase line coverage from ${coverage.total.lines.pct}% to at least 80%`
      });
    }
    
    // Failed test recommendations
    Object.entries(this.testResults).forEach(([type, result]) => {
      if (result && result.status === 'failed') {
        recommendations.push({
          category: 'test-failure',
          severity: 'high',
          issue: `${type} tests failing`,
          recommendation: `Review and fix failing ${type} tests before deployment`
        });
      }
    });
    
    return recommendations;
  }

  parseCoverageReport() {
    try {
      const coveragePath = path.join(process.cwd(), 'coverage/coverage-summary.json');
      if (fs.existsSync(coveragePath)) {
        return JSON.parse(fs.readFileSync(coveragePath, 'utf8'));
      }
    } catch (error) {
      console.warn('Could not parse coverage report:', error.message);
    }
    return null;
  }
}

module.exports = { TestSuiteManager };

Read the full file on GitHub · 936 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. yesterday First seen · 936 lines · 35 tokens per session scan A e25aed318631

Subscribe to this mod's changes

test-engineer is an agent published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 6,211 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens