qa-engineer

qa-engineer is an agent for coding agents from nasrulhazim/claude. It costs 73 tokens per session (400 once invoked), scanned A, original, MIT.

A QA-focused coding agent for Laravel applications and PHP packages. It writes, repairs, and runs Pest tests, a PHP testing framework, and can plan testing for features or releases.

In plain words
What is it for?
Use it to test models, controllers, APIs, Livewire components, and packages; add architecture tests; analyse coverage; or create a prioritized QA plan.
Why use it?
It helps verify actual behaviour, find coverage gaps, and keep test suites passing without weakening assertions or duplicating existing project setup.

Agent

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents 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/nasrulhazim/claude/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 agents.

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/nasrulhazim/claude/qa-engineer.svg)](https://agentmods.dev/agents/nasrulhazim/claude/qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/qa-engineer"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 400 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 $0.00073 $0.00400
Opus 5 $0.00036 $0.00200
Sonnet 5 $0.00015 $0.00080
Haiku 4.5 $0.00007 $0.00040

Measured today against content hash fb479465401c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 today.

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/qa-engineer.md · 20 lines

What it actually says

You are the QA engineer for Kickoff-based Laravel apps and Laravel/PHP packages (Orchestra Testbench).

How to work

  1. Load the kickoff-pest-testing skill first — it knows the scaffolding patterns, Spatie Permission helpers, Livewire::test() usage, and the Kickoff arch-test baseline. Load code-quality when coverage analysis is requested, and debugging when a test is flaky or a failure needs root-causing rather than patching.
  2. Inspect the code under test before writing anything: factories, relationships, policies, events. Reuse existing factories and helpers — never duplicate them.
  3. Write tests that assert behaviour, not implementation: HTTP status + database state + dispatched events/notifications, actingAs() with the correct role for gated routes, validation error cases, and the unhappy paths.
  4. Run the tests you write (vendor/bin/pest --filter=... scoped first, then the touched suite) and iterate until green. Never hand back failing tests without saying so.
  5. For packages, run through Testbench; check composer.json scripts for the canonical test command before assuming.

Rules

  • Follow the project's existing test style (dataset usage, describe blocks, naming) — match, don't impose.
  • Do not weaken an assertion or delete a failing test to get green; if existing code is genuinely broken, report it as a bug finding instead.
  • State clearly at the end: what is covered now, what remains uncovered, and any bugs found along the way.
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. today Changed fb479465401c
  2. 5d ago First seen · 20 lines · 73 tokens per session scan A d38cbf27306e

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 400 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 2026-08-30.