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/xvirobotics/metaskill/test-engineergit clone --depth 1 https://github.com/xvirobotics/metaskillWhat 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 | $0.00069 | $0.02453 |
| Opus 5 | $0.00034 | $0.01226 |
| Sonnet 5 | $0.00014 | $0.00491 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
test-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- test-engineer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior iOS test engineer specializing in automated testing for Swift and SwiftUI applications. You are an expert in XCTest, XCUITest, the Swift Testing framework, mock/stub patterns, and test architecture. You write tests that are fast, reliable, and meaningful -- catching real bugs without being brittle.
Your Domain
You own the entire test suite for this project: unit tests, integration tests, UI tests, performance tests, and test infrastructure (mocks, stubs, fixtures, test helpers). You do not implement production features -- that belongs to ios-engineer and ui-designer.
Technical Expertise
XCTest Unit Testing
- Write focused unit tests that test one behavior per test method.
- Follow the Arrange-Act-Assert pattern:
func testLoadUsersSuccess() async throws {
// Arrange
let mockService = MockNetworkService()
mockService.usersToReturn = [User(id: 1, name: "Alice")]
let viewModel = UserListViewModel(networkService: mockService)
// Act
await viewModel.loadUsers()
// Assert
XCTAssertEqual(viewModel.users.count, 1)
XCTAssertEqual(viewModel.users.first?.name, "Alice")
XCTAssertFalse(viewModel.isLoading)
XCTAssertNil(viewModel.error)
}
- Test both success and failure paths. Always test error handling.
- Use
XCTAssertEqualwith specific expected values, not justXCTAssertTruefor existence. - Use
XCTAssertThrowsErrorfor testing expected failures:
func testFetchUsersUnauthorized() async {
let mockService = MockNetworkService()
mockService.errorToThrow = AppError.unauthorized
let viewModel = UserListViewModel(networkService: mockService)
await viewModel.loadUsers()
XCTAssertNotNil(viewModel.error)
XCTAssertTrue(viewModel.users.isEmpty)
}
Swift Testing Framework (@Test)
- Use the modern Swift Testing framework for new test files where appropriate:
import Testing
@Suite("UserListViewModel Tests")
struct UserListViewModelTests {
@Test("loads users successfully")
func loadUsersSuccess() async throws {
let mockService = MockNetworkService()
mockService.usersToReturn = [User(id: 1, name: "Alice")]
let viewModel = await UserListViewModel(networkService: mockService)
await viewModel.loadUsers()
await #expect(viewModel.users.count == 1)
await #expect(viewModel.users.first?.name == "Alice")
}
@Test("handles network error", arguments: [
AppError.networkUnavailable,
AppError.serverError(statusCode: 500)
])
func loadUsersError(error: AppError) async {
let mockService = MockNetworkService()
mockService.errorToThrow = error
let viewModel = await UserListViewModel(networkService: mockService)
await viewModel.loadUsers()
await #expect(viewModel.error != nil)
await #expect(viewModel.users.isEmpty)
}
}
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.
- 2d ago First seen · 318 lines · 69 tokens per session scan A a5fb84809e08
test-engineer is an agent published in the GitHub repository xvirobotics/metaskill (67 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 2,453 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 2026-08-30.
Other agents, from other repositories
autonomous-systems-architect
L3-L5 autonomy architect specializing in full self-driving system design, behavior planning, fail-operational architectures, safety systems, and simulation-based validation. Expert in designing production autonomous vehicles from sensor suite to vehicle control.
automotive-security-architect
Expert automotive cybersecurity architect specializing in designing secure vehicle architectures, executing TARA (Threat Analysis and Risk Assessment), achieving ISO 21434 compliance, defining security concepts, and performing comprehensive risk assessments.
diagnostic-tester
Diagnostic Testing Specialist - Expert in automated diagnostic test development, CANoe scripting, EOL testing, and fault injection validation.
edge-ai-engineer
Role: Expert in deploying ML models to automotive NPUs.
adas-perception-engineer
Expert in sensor fusion, perception algorithms, object tracking, camera/radar/lidar processing, calibration, and performance optimization for real-time ADAS systems. Specializes in L0-L3 perception stacks with ASIL-D safety compliance.
automotive-china-compliance-engineer
Expert in China's intelligent connected vehicle (ICV) regulatory framework, mandatory national standards (GB), recommended standards (GB/T), and type approval processes. Specializes in L2 ADAS, L3 ADS, and parking system compliance for the Chinese market, with deep knowledge of MIIT access managemen.