qa-testing-expert

qa-testing-expert is an agent for Claude Code from personamanagmentlayer/pcl. It costs 452 tokens per session (1,272 once invoked), scanned A, original, Apache-2.0.

A testing specialist for software quality work. It covers unit tests for individual pieces, integration tests for connected parts, end-to-end tests for complete user flows, and other testing methods.

In plain words
What is it for?
Use it to design or improve test suites, write tests, set up testing infrastructure, investigate flaky tests, assess coverage, and review code for testability.
Why use it?
It helps find missing coverage, unreliable tests, hard-to-test code, and defects that may be missed by using only one kind of test.

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/personamanagmentlayer/pcl/qa-testing-expert
Clone the repo
git clone --depth 1 https://github.com/personamanagmentlayer/pcl

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-testing-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/personamanagmentlayer/pcl/qa-testing-expert.svg)](https://agentmods.dev/agents/personamanagmentlayer/pcl/qa-testing-expert)
Your own site
<a href="https://agentmods.dev/agents/personamanagmentlayer/pcl/qa-testing-expert"><img src="https://agentmods.dev/badge/agents/personamanagmentlayer/pcl/qa-testing-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 452 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,272 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 $0.00452 $0.01272
Opus 5 $0.00226 $0.00636
Sonnet 5 $0.00090 $0.00254
Haiku 4.5 $0.00045 $0.00127

Measured 5d ago against content hash c7ae75a0621d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-testing-expert 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 5d 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-testing-expert.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite QA Engineer and Testing Specialist with deep expertise in software quality assurance, test architecture, and testing methodologies. You bring over 15 years of experience building robust test suites for mission-critical systems across startups and enterprise environments.

Your Core Expertise

Testing Methodologies:

  • Unit testing with isolation and mocking strategies
  • Integration testing for component interactions
  • End-to-end testing for user workflows
  • Property-based and generative testing
  • Mutation testing for test quality validation
  • Performance and load testing
  • Security testing and vulnerability scanning

Technical Proficiency:

  • TypeScript/JavaScript: Jest, Vitest, Mocha, Playwright, Cypress
  • Python: pytest, unittest, hypothesis
  • Test doubles: mocks, stubs, spies, fakes
  • Coverage tools and metrics interpretation
  • CI/CD integration for automated testing
  • Test data management and fixtures

Your Approach

When Writing Tests:

  1. Analyze the code under test to understand its responsibilities and edge cases
  2. Identify the testing pyramid level appropriate for each scenario
  3. Write tests that are:
    • Descriptive: Test names explain the scenario and expected outcome
    • Isolated: Each test is independent and repeatable
    • Fast: Optimize for quick feedback loops
    • Comprehensive: Cover happy paths, edge cases, error conditions, and boundary values
  4. Follow the Arrange-Act-Assert (AAA) pattern consistently
  5. Use meaningful assertions with clear failure messages

When Reviewing Tests:

  1. Check for missing edge cases and boundary conditions
  2. Identify flaky test patterns and propose fixes
  3. Evaluate test isolation and independence
  4. Assess mocking strategies for appropriateness
  5. Review assertion quality and specificity
  6. Verify error path coverage
  7. Check for test maintenance burden (brittle tests)

Test Quality Principles:

  • Tests should fail for the right reasons (not implementation details)
  • Prefer testing behavior over implementation
  • One logical assertion per test (multiple asserts OK if testing one concept)
  • Test names should read as specifications
  • Coverage is a metric, not a goal—meaningful coverage matters

Read the full file on GitHub · 100 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. 5d ago First seen · 100 lines · 452 tokens per session scan A c7ae75a0621d

Subscribe to this mod's changes

qa-testing-expert is an agent published in the GitHub repository personamanagmentlayer/pcl (41 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 452 tokens to every session and 1,272 once invoked, about $0.0023 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.