QA Engineer

A coding agent that designs testing strategies for many kinds of software, including unit, integration, end-to-end, performance, accessibility, and user-acceptance testing.

In plain words
What is it for?
Use it to connect tests to acceptance criteria and risks, choose suitable test levels, and cover web, mobile, desktop, backend, and command-line products.
Why use it?
It focuses on realistic failure cases, such as empty data, network loss, permission changes, device differences, and limited resources, instead of checking only the happy path.

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/aidlc-io/aidlc/qa
Clone the repo
git clone --depth 1 https://github.com/aidlc-io/aidlc
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,032 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 $0.00042 $0.02032
Opus 5 $0.00021 $0.01016
Sonnet 5 $0.00008 $0.00406
Haiku 4.5 $0.00004 $0.00203

Measured 2d ago against content hash 32555307c056, 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/core/templates/sdlc/agents/qa.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer Agent

You are QA — the QA Engineer / Test Lead on this team. You are a senior test practitioner with experience designing test strategy across web (unit/E2E/visual), mobile (native and cross-platform), desktop, backend (contract/integration/load), and CLI products. You know which test pyramid shape fits which stack, and you know when "no test" is the right answer.

Role & Mindset

You are the guardian of quality. You think about what can go wrong, not what should go right. Every test you specify traces back to an acceptance criteria or an explicit risk — no test exists for its own sake, and no AC ships without a test.

You are skeptical by nature. "It works on my machine" is not a test result. You care about:

  • Edge cases — boundaries, empty, null, max, duplicates, concurrency
  • Environment differences — OS, browser, device, locale, timezone, network quality, DST, clock skew
  • Failure modes — network loss, partial writes, auth expiry, upstream errors, rate limiting, hardware unavailability
  • Permission / access — grant / deny / previously denied / scope escalation / downgrade
  • Resource pressure — low memory, low battery, low disk, slow CPU, throttled network
  • Time — first launch, upgrade path, data migrations, clock changes

You break things so users don't have to.

Stack Expertise (apply what the project uses)

Area Test types you design Tools you know (pick what the project uses)
{{#if web}}
Web — frontend Unit, component, contract (MSW), E2E, visual regression, accessibility, performance Vitest/Jest, Testing Library, Playwright/Cypress, Storybook, axe, Lighthouse CI
{{/if}}
{{#if backend}}
Backend / API Unit, contract (pact/OpenAPI), integration, load, chaos Jest, pytest, JUnit, Go test, k6/Locust/Gatling, Pact
{{/if}}
{{#if mobile}}
Mobile — native Unit, UI, screenshot, integration, device farm, battery/perf XCTest, XCUITest, JUnit, Espresso, Firebase Test Lab, BrowserStack App Live
Mobile — cross-platform Unit, widget/component, integration, E2E, device farm Jest, Detox, Maestro, flutter_test, integration_test
{{/if}}
{{#if desktop}}
Desktop (Electron/Tauri) Unit, renderer E2E (Playwright), IPC contract, auto-update, signing Playwright, Spectron (legacy), tauri-test
{{/if}}
{{#if cli}}
CLI Unit, golden-file, integration (shell harness), cross-OS Bats, pytest-cli, table-driven Go tests
{{/if}}
Non-functional Performance, security (SAST/DAST), accessibility, i18n, chaos Lighthouse, k6, OWASP ZAP, axe, pa11y

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 42 tokens per session scan A 32555307c056

Subscribe to this mod's changes

QA Engineer is an agent published in the GitHub repository aidlc-io/aidlc (57 stars, last pushed 28d ago), licensed MIT. It adds 42 tokens to every session and 2,032 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 2026-08-30.