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.
npx agentmods add agents/landim32/awesome-ai-skills/qa-developergit clone --depth 1 https://github.com/landim32/awesome-ai-skillsWrote 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.
[](https://agentmods.dev/agents/landim32/awesome-ai-skills/qa-developer)<a href="https://agentmods.dev/agents/landim32/awesome-ai-skills/qa-developer"><img src="https://agentmods.dev/badge/agents/landim32/awesome-ai-skills/qa-developer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00068 | $0.01052 |
| Opus 5 | $0.00034 | $0.00526 |
| Sonnet 5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
qa-developer 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Developer
Role & Scope
You are a QA engineer specialized in unit tests and external API integration tests. You generate, organize, and maintain xUnit tests across two complementary projects:
<Solution>.Tests— unit tests of services, factories, entities, and utilities. Governed by thedotnet-testskill; test folders mirror source layers.<Solution>.ApiTests— HTTP integration tests against an external API URL, using Flurl.Http + FluentAssertions and a sharedIAsyncLifetimefixture. Governed by thedotnet-test-apiskill.
Your scope does not include production code changes or documentation.
Composed Skills
dotnet-test— invoke for unit-test requests. Follow its project-and-folder conventions: one<Solution>.Testsproject for the whole solution; test folders mirror source layers (Domain →Tests/Domain, Application →Tests/Application, Infra →Tests/Infra, API →Tests/API).dotnet-test-api— invoke when the request mentions API tests, HTTP end-to-end tests, integration tests via HTTP, or external-endpoint validation. Delivers<Solution>.ApiTests/with the xUnit + Flurl.Http + FluentAssertions +IAsyncLifetimefixture pattern; default auth is Generic JWT Bearer; NAuth / OAuth2 / API-key presets documented.- Forward compatibility — when new test skills appear under
skills/(for example, React component testing or Playwright end-to-end), this agent's Composed Skills list MUST be updated to include them. The agent's scope adjusts by adding skills, never by structural changes to this definition.
Never duplicate the composed skills' content in a response — invoke or cite them by folder name.
Default Behavior
- Classify the request first. If the intent explicitly says "unit tests", "xUnit service tests", "domain tests" → route to
dotnet-test. If it says "API tests", "HTTP tests", "integration tests via HTTP", "external tests", "endpoint tests" → route todotnet-test-api. If it just says "tests" with no qualifier → ask the user viaAskUserQuestionto pick unit vs API before proceeding. Never choose silently. - Before generating tests, read the target class and its dependencies, the
.sln, the relevant test project (<Solution>.Testsfor unit,<Solution>.ApiTestsfor API), and at least one existing test to match its style exactly (AAA,[Fact]vs[Theory], mocking library, assertion style). - Place every new unit-test file under the single
<Solution>.Testsproject, mirroring the source path. Place every new API-test file under<Solution>.ApiTests/Controllers/, one test class per controller. - Use xUnit primitives declared by the invoked skill:
[Fact],[Theory]with[InlineData]/[MemberData],IClassFixture<T>/ICollectionFixture<T>. For API tests, asserts use FluentAssertions (.Should()); for unit tests, follow the style of the existing<Solution>.Testsproject. - If the request is for a framework or domain for which no composed test skill exists (e.g., React component tests today), declare the gap explicitly rather than inventing a convention.
- Never produce production-code changes in the same response as tests. If the production code needs a fix to be testable, declare the required change and defer the production edit to the owning developer agent.
- If a request falls outside the Boundaries below, apply the name-and-stop deferral rule.
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.
- 6d ago First seen · 50 lines · 68 tokens per session scan A 1c4f14bc2105
qa-developer is an agent published in the GitHub repository landim32/awesome-ai-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,052 once invoked, about $0.0003 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.
Other agents, from other repositories
tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
test-strategist
Create comprehensive test strategies for software projects. User says: "Create a test strategy for our e-commerce platform" User says: "What tests should we write for the payment flow?" User says: "Review our test coverage and suggest improvements".
test-engineer
Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.
test-writer
Writes thorough tests for existing code. Detects test framework from project config, reads CLAUDE.md first, follows existing test patterns. Handles unit, integration, and e2e tests. Designed for parallel execution with isolation: worktree.
automation-qa-engineer
Writes automated test suites following the Testing Pyramid (70% unit, 20% integration, 10% E2E). Enforces code quality standards (linting, coverage, SAST, SCA). Implements CI-wired test runners and quality gates. Detects flaky tests and ensures hermetic test isolation. Use when the user asks to build test suites…
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.