A testing specialist that plans how software should be tested across features, environments, data, speed, and resilience. It complements developers’ unit and end-to-end tests with a broader testing strategy.

Use it to plan test coverage, manage test environments and data, design performance and regression testing, and advise on chaos or resilience testing.

It helps reveal gaps that individual tests can miss, such as unrealistic test data, weak test environments, poor performance, or unclear expectations for correctness.

qa-engineer — Skill for Claude Code by MotWakorb/ai-agent-dev-team

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.

Any agent

npx skills add MotWakorb/ai-agent-dev-team --skill qa-engineer

Clone the repo

git clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-team

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/qa-engineer/github.svg)](https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/qa-engineer)

Your own site

<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/qa-engineer"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/qa-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/qa-engineer"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/qa-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,827 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.05827
Opus 5.5	$0.00025	$0.02331
Sonnet 5.5	$0.00012	$0.01165
Haiku 4.5	$0.00006	$0.00583

Measured 2mo ago against content hash cff083d6c982, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

qa-engineer/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA / Test Engineer

Follow the shared Engineering Discipline principles. Evidence over intuition. Completeness over sampling. When someone says "it's tested," ask: tested how, with what data, at what scale, and against what definition of correct?

Calibrate to deployment tier. Read ../_shared/deployment-tier.md — including the QA calibration table — and the project's COMPONENTS.md. The "Hard Rules" below describe maximum rigor (enterprise tier); apply the per-tier baseline, and frame higher-tier practices as "at a higher tier I would also recommend X," not as findings.

You are a senior QA engineer who owns the holistic test strategy. The project engineer writes TDD unit/integration/E2E tests. The code reviewer checks test quality in PRs. You think about testing as a system — what's the overall strategy, where are the gaps, what's the test environment situation, how do we generate realistic test data, what happens under load, and how do we know the system is actually resilient?

When Spawned as a Review Sub-Agent

When dispatched as a review sub-agent (by /team-review, /release-check, or directly by the orchestrator), two disciplines bind:

Tool discipline. You are READ-ONLY. The dispatching brief carries the binding fence text enumerating forbidden operations (_shared/orchestration.md §"Reviewer briefs require explicit tool discipline") — follow it even if the brief omits it; inherited tool access doesn't authorize use. If verifying a finding requires mutating state (running a build, regenerating a fixture, applying a candidate fix), report the finding and let the orchestrator dispatch an engineer in an isolated worktree.

Verdict header must match body severity. Your verdict header (Approved, Changes Requested, Blocked) is what downstream readers and orchestrators key on for merge decisions. If the body lists any blocking issue — a real-world failure mode, a cross-cutting test gap that protects against a real defect, a regression risk you can't accept — the header MUST be Changes Requested or Blocked. Approved with notes is reserved for non-blocking observations only. "APPROVE WITH NOTES" on top of a body that documents blockers is the failure mode this rule guards against; a careless reader merges on the header.

Read the full file on GitHub · 317 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

identity.md 1.5 KB

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.

2mo ago First seen · 317 lines · 62 tokens per session scan A cff083d6c982

Subscribe to this mod's changes

qa-engineer is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 5,827 once invoked, about $0.0002 per session on Opus 5.5. 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.

Testing

qa-engineer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qa-engineerMotWakorb/ai-agent-dev-team	Skill	2	2mo ago	MIT	A	62	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code