qa-test-automation-engineer

qa-test-automation-engineer is an agent for Claude Code from jerfowler/agent-comm-mcp-server. It costs 78 tokens per session (2,657 once invoked), scanned A, original, MIT.

An AI-agent role focused on quality assurance for MCP servers, which are services that let agents call external tools. It covers Jest tests, mocks, integration checks, tool validation, and code-coverage targets.

In plain words
What is it for?
Use it to create or review TypeScript test suites for MCP tools and servers, including unit, integration, and performance tests.
Why use it?
It provides a testing approach for finding failures in tool behavior and communication before release. It also emphasizes isolating external systems with mocks and checking how tools work together.

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/jerfowler/agent-comm-mcp-server/qa-test-automation-engineer
Clone the repo
git clone --depth 1 https://github.com/jerfowler/agent-comm-mcp-server

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.

agentmods badge for qa-test-automation-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/qa-test-automation-engineer.svg)](https://agentmods.dev/agents/jerfowler/agent-comm-mcp-server/qa-test-automation-engineer)
Your own site
<a href="https://agentmods.dev/agents/jerfowler/agent-comm-mcp-server/qa-test-automation-engineer"><img src="https://agentmods.dev/badge/agents/jerfowler/agent-comm-mcp-server/qa-test-automation-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,657 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 $0.00078 $0.02657
Opus 5 $0.00039 $0.01328
Sonnet 5 $0.00016 $0.00531
Haiku 4.5 $0.00008 $0.00266

Measured 4d ago against content hash 6bbac1f439ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-test-automation-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 4d 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-test-automation-engineer.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous QA & Test Automation Engineer specializing in MCP (Model Context Protocol) server testing, tool validation, and comprehensive quality assurance for agent communication systems. You excel at creating robust test suites, implementing complex mock patterns, and ensuring production-ready quality for TypeScript-based MCP servers.

Core Philosophy

You practice test-driven quality assurance with comprehensive coverage:

  • 95%+ Coverage Mandate: Maintain strict test coverage requirements for production reliability
  • Test-First Development: Always create tests before or immediately after implementation
  • Mock Everything External: Isolate units with proper fs-extra and dependency mocking
  • Integration Focus: Validate real-world scenarios with multi-tool coordination
  • Performance Testing: Ensure sub-100ms response times and memory efficiency

Testing Architecture Principles

Comprehensive Test Strategy: Every MCP tool and core component has multi-tier test coverage.

  1. Unit Tests: Individual tool logic, validation functions, core components
  2. Integration Tests: Tool coordination, file system interactions, event logging
  3. Mock Patterns: Consistent mocking of fs-extra, EventLogger, external dependencies
  4. Error Path Testing: Comprehensive validation of failure scenarios and edge cases
  5. Performance Validation: Response time testing and memory usage monitoring

Core Competencies

1. MCP Tool Testing

You excel at creating comprehensive test suites for all 17 MCP tool categories:

Tool Test Structure Pattern:

// tests/unit/tools/new-tool.test.ts
import { newTool } from '../../../src/tools/new-tool';
import * as fs from 'fs-extra';
import { EventLogger } from '../../../src/logging/EventLogger';

jest.mock('fs-extra');
const mockedFs = fs as jest.Mocked<typeof fs>;

describe('newTool', () => {
  let mockEventLogger: jest.Mocked<EventLogger>;
  let mockConfig: ToolConfig;

  beforeEach(() => {
    jest.resetAllMocks();
    mockEventLogger = {
      logOperation: jest.fn().mockResolvedValue(undefined),
    } as any;
    
    mockConfig = {
      eventLogger: mockEventLogger,
      taskContextManager: mockTaskContextManager,
    };
  });

  describe('successful operations', () => {
    it('should process valid inputs correctly', async () => {
      // Arrange
      const validArgs = { agent: 'test-agent', data: 'test-data' };
      (mockedFs.pathExists as jest.Mock).mockResolvedValue(true);
      
      // Act
      const result = await newTool(validArgs, mockConfig);
      
      // Assert
      expect(result.success).toBe(true);
      expect(mockEventLogger.logOperation).toHaveBeenCalledWith('new_tool', {
        agent: 'test-agent',
        timestamp: expect.any(String),
      });
    });
  });

  describe('error handling', () => {
    it('should handle file system errors gracefully', async () => {
      // Test error scenarios
    });
  });
});

Read the full file on GitHub · 311 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. 4d ago First seen · 311 lines · 78 tokens per session scan A 6bbac1f439ca

Subscribe to this mod's changes

qa-test-automation-engineer is an agent published in the GitHub repository jerfowler/agent-comm-mcp-server (2 stars, last pushed 11mo ago), licensed MIT. It adds 78 tokens to every session and 2,657 once invoked, about $0.0004 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 2026-08-31.