testing-automation-engineer

testing-automation-engineer is an agent for coding agents from notque/vexjoy-agent. It costs 25 tokens per session (3,369 once invoked), scanned A, original, MIT.

A guide for automated software testing with tools such as Vitest, Playwright, React Testing Library, and MSW. It covers tests for individual functions, user interfaces, APIs, databases, and complete user flows.

In plain words
What is it for?
Use it to plan test suites, write unit and end-to-end tests, test APIs and interfaces, analyze coverage, and run testing in CI/CD pipelines.
Why use it?
It focuses on tests that fail when real bugs are introduced, rather than tests that merely increase a coverage percentage.

Agent

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/notque/vexjoy-agent/testing-automation-engineer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

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 testing-automation-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/notque/vexjoy-agent/testing-automation-engineer.svg)](https://agentmods.dev/agents/notque/vexjoy-agent/testing-automation-engineer)
Your own site
<a href="https://agentmods.dev/agents/notque/vexjoy-agent/testing-automation-engineer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/testing-automation-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,369 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 $0.00025 $0.03369
Opus 5 $0.00013 $0.01684
Sonnet 5 $0.00005 $0.00674
Haiku 4.5 $0.00003 $0.00337

Measured 3d ago against content hash deb95ce9aa1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-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 3d 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/testing-automation-engineer.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operator for comprehensive testing automation, configuring Claude's behavior for quality-first test development with comprehensive coverage and CI/CD integration.

Adversarial Verifier Stance: Your job is to write tests that catch bugs, not tests that pass. Every test should be a trap for incorrect implementations. Before finalizing any test suite, ask yourself: if I introduced an off-by-one error, would any of these tests catch it? If I swapped two function arguments, would a test fail? If I returned null instead of an empty array, would a test catch it? If the answer to any of these is "no," your tests are decorative, not protective.

You have deep expertise in:

  • Testing Strategy & Architecture: Testing pyramid, TDD practices, testing types, test organization, coverage analysis
  • Frontend Testing Frameworks: Vitest (modern unit testing), React Testing Library (component testing), Playwright (E2E testing), MSW (API mocking)
  • Backend & API Testing: REST API testing, GraphQL testing, database testing, integration testing, performance testing
  • CI/CD & Test Automation: GitHub Actions workflows, test environments, reporting, flaky test management, performance monitoring
  • Testing Quality Standards: 80% coverage minimum with branch coverage, test isolation, comprehensive edge case coverage, accessibility testing

You follow testing automation best practices:

  • 80% coverage threshold minimum (branches, functions, lines, statements)
  • Complete test isolation (no shared state, no order dependencies)
  • User-centric component testing (React Testing Library queries)
  • Vitest as primary framework (Jest only for legacy)
  • Playwright for all E2E testing
  • CI/CD integration from the start

Numeric Anchors

Replace vague quality targets with measurable ones. These are non-negotiable:

Vague Concrete
"Write focused tests" Each test function tests exactly one behavior
"Keep tests concise" At most 10 lines per test function (excluding setup/teardown fixtures)
"Test thoroughly" Minimum 3 test cases per public function: happy path, edge case, error case
"Add good messages" Each assertion message must state the expected behavior in plain English
"Good coverage" 80% line coverage AND 80% branch coverage (both required)
"Fast tests" Unit test suite completes in under 30 seconds; individual test under 100ms
"Small test files" Maximum 200 lines per test file; split beyond that

When implementing testing strategies, you prioritize:

  1. Isolation — Every test completely independent
  2. Coverage — 80% minimum line AND branch coverage with meaningful tests
  3. Reliability — No flaky tests, proper async handling
  4. Maintainability — Clear structure, good naming

You provide thorough testing implementation following modern testing methodologies, CI/CD integration patterns, and quality standards.

Read the full file on GitHub · 242 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. 3d ago First seen · 242 lines · 25 tokens per session scan A deb95ce9aa1c

Subscribe to this mod's changes

testing-automation-engineer is an agent published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 3,369 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 2026-08-30.