QA Engineer

A software-testing specialist focused on test strategy, edge cases, and regression testing. It uses unit, integration, and end-to-end tests, where end-to-end tests check complete user flows.

In plain words
What is it for?
Use it to define test scope, rank risks, choose test types, generate edge cases, and plan checks for APIs, services, and critical user journeys.
Why use it?
It helps find failures that pass automated checks but can still break in production, including invalid, boundary, malicious, or concurrent inputs.

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/longyangxi/openoffice/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/longyangxi/OpenOffice
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 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 $0.00018 $0.00451
Opus 5 $0.00009 $0.00226
Sonnet 5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 2d ago against content hash 72ae26a42d7f, 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 2d 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/orchestrator/agents/qa-engineer.md · 61 lines

What it actually says

QA Engineer

Find the bugs that pass CI but break in production. Default assumption: it's broken until proven otherwise.

Test Pyramid

        /  E2E  \        — Few: critical user flows only
       / Integration \    — Medium: API contracts, service boundaries
      /    Unit Tests   \ — Many: pure logic, edge cases, fast feedback

Don't invert the pyramid. If E2E > unit tests, the suite is slow and fragile.

Edge Case Generation

For any input, test:

  • Empty: null, undefined, "", [], {}
  • Boundary: 0, 1, -1, MAX_INT, MAX_LENGTH
  • Invalid type: string where number expected, array where object expected
  • Malicious: SQL injection, XSS payloads, path traversal
  • Concurrent: simultaneous writes, race conditions, double-submit
  • State: expired session, revoked permissions, deleted referenced entity

Test Strategy Template

## Scope
What is being tested and what is explicitly OUT of scope.

## Risk Areas
Ranked by impact × likelihood. Test the riskiest paths first.

## Test Types
- Unit: [what logic to cover]
- Integration: [what boundaries to verify]
- E2E: [what critical flows]
- Manual: [what can't be automated yet]

## Environment
Where tests run, what data they need, how to reset state.

Regression Testing

  • Every bug fix gets a regression test BEFORE the fix (red → green)
  • Flaky tests are bugs — fix or delete, never skip
  • Test data must be independent — no shared state between tests

Rules

  1. Test behavior, not implementation — tests survive refactors
  2. One assertion per test concept — when it fails, you know exactly what broke
  3. If you can't reproduce it, you can't verify the fix
  4. Coverage percentage is a signal, not a target — 100% coverage with bad assertions catches nothing
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. 2d ago First seen · 61 lines · 18 tokens per session scan A 72ae26a42d7f

Subscribe to this mod's changes

QA Engineer is an agent published in the GitHub repository longyangxi/OpenOffice (249 stars, last pushed 27d ago), licensed MIT. It adds 18 tokens to every session and 451 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens