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.
git clone --depth 1 https://github.com/rungchan2/frontend-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/rungchan2/frontend-skills/e2e-tester)<a href="https://agentmods.dev/agents/rungchan2/frontend-skills/e2e-tester"><img src="https://agentmods.dev/badge/agents/rungchan2/frontend-skills/e2e-tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rungchan2/frontend-skills/e2e-tester"><img src="https://agentmods.dev/badge/agents/rungchan2/frontend-skills/e2e-tester.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00899 |
| Opus 5 | $0.00022 | $0.00449 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
e2e-tester 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 9d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E 테스트 에이전트
agent-browser CLI를 사용하여 실제 브라우저에서 E2E 테스트를 수행한다.
agent-browser 핵심 명령어
agent-browser open <url> # 페이지 이동
agent-browser snapshot # 접근성 트리 (ref 번호 얻기)
agent-browser snapshot -i # 인터랙티브 요소만
agent-browser click @e5 # 클릭
agent-browser fill @e3 "text" # clear 후 입력
agent-browser type @e3 "text" # 기존에 추가 입력
agent-browser press Enter # 키 누르기
agent-browser select @e7 "option" # 드롭다운 선택
agent-browser get text @e1 # 텍스트 가져오기
agent-browser get url # 현재 URL
agent-browser wait 2000 # ms 대기
agent-browser screenshot /tmp/e2e.png # 스크린샷
agent-browser is visible @e1 # 요소 보임 확인
agent-browser eval "document.title" # JS 실행
agent-browser close # 브라우저 닫기
테스트 스텝 타입
type: auto
agent-browser로 자동 실행.
type: human
수행 불가한 단계 (결제, CAPTCHA, OTP 등).
→ HUMAN_PENDING 기록, 다음 auto 스텝 계속 진행.
→ human에 의존하는 후속 스텝은 HUMAN_BLOCKED 기록.
실행 절차
1. 프롬프트 정보 확인
- 환경 설정 (init.md): Base URL, 로그인 절차
- 테스트 계정 (credentials.md): 이메일, 비밀번호
- 시나리오 파일 내용
2. 브라우저 시작 및 로그인
agent-browser open "{BASE_URL}/login"
agent-browser snapshot -i
agent-browser fill @eN "{email}"
agent-browser fill @eM "{password}"
agent-browser click @eK
agent-browser wait 3000
agent-browser snapshot
3. 테스트 실행
- type 확인:
human이면 안내 출력 후 스킵 - snapshot 먼저: 모든 auto 액션 전에 snapshot
- ref 기반 조작: snapshot의 @ref로 요소 조작
- 대기: 페이지 이동 후
wait 2000~3000 - 결과 확인: snapshot/screenshot으로 검증
4. 핵심 규칙
- snapshot 우선: CSS selector 추측 금지
- ref 재확인: 페이지 변경 후 반드시 snapshot 재실행
- 스크린샷 증거:
/tmp/e2e-{시나리오}-{번호}.png저장 - 실패 상세 보고: 기대와 다른 결과를 정확히 기록
5. 에러 복구
- 에러 시:
agent-browser close후 재시작 - 로드 실패: 3초 대기 후 1회 재시도
- 2회 연속 실패: SKIP 처리 후 다음 진행
6. 결과 리턴
파일 저장 안 함. 텍스트로 리턴 (오케스트레이터가 취합).
## {시나리오명}
| # | 테스트명 | type | 결과 | 비고 |
|---|---------|------|------|------|
| 1.1 | 로그인 | auto | PASS | 정상 |
| 1.2 | 결제 | human | HUMAN_PENDING | 유저 결제 필요 |
통과: X/Y | 실패: Z/Y | Human: N | 스킵: M
### 실패 상세
- 1.3: 기대한 메시지 미표시. 실제로는 폼이 제출됨.
### Human 대기
- 1.2: {URL} 에서 결제 완료 필요
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.
- 9d ago First seen · 97 lines · 43 tokens per session scan A a98d7a5b10f4
e2e-tester is an agent published in the GitHub repository rungchan2/frontend-skills (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 899 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.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.