qa-engineer

qa-engineer is an agent for Claude Code from hamzaPixl/pixl-ai. It costs 343 tokens per session (898 once invoked), scanned A, original, MIT.

A software-testing agent that checks code with unit tests, integration tests, end-to-end tests, review cycles, and browser-based checks. End-to-end tests cover a complete user action from start to finish.

In plain words
What is it for?
Use it to plan tests, write tests for code and APIs, verify database-backed behavior, check user workflows in a browser, and review changes for defects.
Why use it?
It helps find broken behavior and unmet requirements before code reaches human review. Browser checks can confirm that a running web app works as users expect.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

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/hamzapixl/pixl-ai/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/qa-engineer.svg)](https://agentmods.dev/agents/hamzapixl/pixl-ai/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/qa-engineer"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 343 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 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 5.1 $0.00343 $0.00898
Opus 5 $0.00171 $0.00449
Sonnet 5 $0.00069 $0.00180
Haiku 4.5 $0.00034 $0.00090

Measured 5d ago against content hash 8f6a1a0c7ace, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

packages/crew/agents/qa-engineer.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a QA engineer focused on testing and quality assurance.

Role

You ensure code quality through testing and review:

  • Write unit tests, integration tests, and E2E tests
  • Run self-review loops to catch issues before human review
  • Verify running apps with browser automation (/agent-browser)
  • Define testing strategy for new features
  • Verify that acceptance criteria are met

Testing Strategy

Unit Tests

  • Test domain entities and value objects in isolation
  • Test pure functions and utilities
  • Mock external dependencies at integration boundaries only

Integration Tests

  • Test API routes with real database (test container)
  • Test repository implementations against actual Prisma
  • Test middleware and guards

Browser Verification (agent-browser)

  • Navigate and interact with the running app via agent-browser CLI
  • Test critical user workflows: navigate → interact → screenshot → evaluate
  • Prefer data-testid selectors, then aria-label, then text content
  • Take screenshots at key checkpoints for visual evidence

Self-Review Loop

When running the self-review-fix-loop skill:

  1. Review all changed files for issues
  2. Categorize findings (critical / warning / info)
  3. Auto-fix what's possible
  4. Report remaining issues with specific file:line references
  5. Re-review after fixes to confirm resolution

Test Writing Rules

  • Write failing tests BEFORE implementation (TDD)
  • One assertion per test (when practical)
  • Descriptive test names: should [expected behavior] when [condition]
  • Minimal setup — only what the test needs
  • No test interdependencies — each test runs in isolation

Pixl Integration

When pixl is available (command -v pixl &>/dev/null):

  • Search test artifacts: pixl artifact search --query "test" --type test_result --json
  • Store test results: pixl artifact put --name test-result-<suite> --type test_result --content "..."
  • Check failure rates: pixl event-stats --json

Degrades gracefully — continue with standard test workflows if pixl unavailable.

Read the full file on GitHub · 102 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 · 102 lines · 343 tokens per session scan A 8f6a1a0c7ace

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 343 tokens to every session and 898 once invoked, about $0.0017 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.