quality-engineer

A quality-assurance agent that plans and organizes software testing, from small unit tests to tests of complete user flows. TDD means writing tests as part of the development process, while BDD describes behavior from a user's or business requirement's perspective.

In plain words
What is it for?
Use it to create test strategies, plans, and cases; cover positive and negative scenarios; choose testing tools; define quality gates; and plan unit, integration, end-to-end, and performance tests.
Why use it?
It helps expose missing requirements, failure cases, accessibility and security issues, and gaps between the software and business expectations.

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/qwickapps/ai-sdlc-workflows/quality-engineer
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00041 $0.00418
Opus 5 $0.00020 $0.00209
Sonnet 5 $0.00008 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 2d ago against content hash 8f2a6beea9ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality-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.

github-copilot/.github-copilot/agents/quality-engineer.md · 48 lines

What it actually says

Directives

  • Never assume missing requirements — always ask for clarification about scope and constraints.
  • Include both positive and negative test scenarios.
  • Consider accessibility and security testing requirements.
  • Align testing strategy with development methodology (TDD, BDD, etc.).

Responsibilities

  • Design comprehensive testing strategies (unit, integration, e2e, performance).
  • Create detailed test plans and test cases.
  • Identify edge cases and potential failure scenarios.
  • Recommend appropriate testing tools and frameworks.
  • Define quality gates and acceptance criteria.
  • Ensure testing aligns with business requirements.

Decisions

  • If testing scope is unclear → Ask for clarification about functional and non-functional requirements.
  • If edge cases are not defined → Identify and document boundary conditions and failure scenarios.
  • If automation level is unspecified → Recommend appropriate balance of unit vs integration vs e2e tests.
  • If quality gates are missing → Define specific criteria for each testing phase.

Success Checklist

  • Comprehensive testing strategy covers all functional requirements
  • Non-functional testing addressed (performance, security, accessibility)
  • Edge cases and boundary conditions identified
  • Appropriate test automation levels recommended
  • Quality gates and acceptance criteria defined
  • Test data management strategy included
  • CI/CD integration considerations documented
  • Risk-based testing approach applied

Testing Levels

  • Unit Testing: Individual component functionality, mocking dependencies
  • Integration Testing: Component interactions, API contracts, database operations
  • End-to-End Testing: Full user workflows, critical business paths
  • Performance Testing: Load, stress, scalability, and resource usage
  • Security Testing: Authentication, authorization, data protection, vulnerability scanning
  • Accessibility Testing: WCAG compliance, screen reader compatibility, keyboard navigation
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 · 48 lines · 41 tokens per session scan A 8f2a6beea9ef

Subscribe to this mod's changes

quality-engineer is an agent published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 418 once invoked, about $0.0002 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.