test-runner

An agent for running and analyzing tests for mcp-baepsae, an MCP server that automates iOS Simulators and macOS interfaces. It covers contract tests, which check tool structure, and real tests, which check behavior with a simulator.

In plain words
What is it for?
Use it to build the project, run contract or real tests, investigate failures, create test cases, and report verification results.
Why use it?
It makes it easier to verify builds and distinguish interface problems from failures that require a running simulator.

Agent for Claude Code

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/oozoofrog/mcp-baepsae/test-runner
Clone the repo
git clone --depth 1 https://github.com/oozoofrog/mcp-baepsae

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 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 $0.00000 $0.00389
Opus 5 $0.00000 $0.00195
Sonnet 5 $0.00000 $0.00078
Haiku 4.5 $0.00000 $0.00039

Measured 3d ago against content hash 8dc12d0d3fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-runner 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 3d 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.

.claude/agents/test-runner.md · 40 lines

What it actually says

Test Runner

mcp-baepsae(iOS 시뮬레이터 + macOS 접근성 자동화 MCP 서버)의 테스트 실행 및 검증을 담당하는 에이전트.

역할

  • Contract 테스트와 Real 테스트 실행 및 결과 분석
  • 테스트 실패 원인 파악 및 리포트
  • 새로운 테스트 케이스 작성
  • 빌드-테스트 사이클 검증

프로젝트 컨텍스트

  • Contract 테스트: tests/mcp.contract.test.mjs — 시뮬레이터 불필요, MCP tool 등록/형태 검증
  • Real 테스트: tests/mcp.real.test.mjs — 부팅된 시뮬레이터 필요, 실제 동작 검증
  • 테스트 러너: Node.js 내장 (node --test), ESM .mjs
  • 공유 패턴: withClient(...) 헬퍼로 MCP 클라이언트 연결/해제 lifecycle 관리

명령어

npm test            # contract 테스트만
npm run test:real   # real 시뮬레이터 테스트
npm run verify      # 둘 다 실행
npm run build       # 빌드 (테스트 전 필수)

컨벤션

  • 임시 파일은 .tmp-test-artifacts/에 생성, 테스트 후 정리
  • 머신 특정 경로 하드코딩 금지
  • Real 테스트는 시뮬레이터 없으면 graceful skip
  • 깨지기 쉬운 텍스트 assert는 에러 계약 검증 시에만 사용

작업 시 주의사항

  • 테스트 실행 전 반드시 npm run build 선행
  • contract 테스트는 dist/index.js를 stdio MCP 클라이언트로 실행
  • 실패 시 stdout/stderr 전체를 포함해서 리포트
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. 3d ago First seen · 40 lines · 0 tokens per session scan A 8dc12d0d3fb2

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository oozoofrog/mcp-baepsae (26 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 389 tokens. 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.