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 skills/jh941213/codex-lattice/e2e-agent-browsernpx skills add jh941213/codex-lattice --skill e2e-agent-browsergit clone --depth 1 https://github.com/jh941213/codex-latticeWrote 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/skills/jh941213/codex-lattice/e2e-agent-browser)<a href="https://agentmods.dev/skills/jh941213/codex-lattice/e2e-agent-browser"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/e2e-agent-browser.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 | $0.00113 | $0.03596 |
| Opus 5 | $0.00056 | $0.01798 |
| Sonnet 5 | $0.00023 | $0.00719 |
| Haiku 4.5 | $0.00011 | $0.00360 |
Grade A, and why
e2e-agent-browser scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { execSync } = require('child_process'); How it starts
The opening of the file, as written. The whole thing — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Testing with agent-browser
AI 에이전트를 위한 헤드리스 브라우저 자동화 CLI agent-browser를 활용하여 E2E 테스트를 작성하고 실행하는 종합 가이드입니다.
이 스킬을 사용할 때
- 웹 애플리케이션 E2E 테스트 작성
- 로그인/회원가입 플로우 테스트
- 폼 입력 및 제출 테스트
- 네비게이션 및 라우팅 테스트
- UI 상호작용 테스트 (클릭, 호버, 스크롤)
- 시각적 상태 확인 (요소 존재, 텍스트 내용)
- CI/CD 파이프라인에서 브라우저 테스트 실행
설치
# npm으로 설치 (권장)
npm install -g agent-browser
# Chromium 브라우저 다운로드
agent-browser setup
# Linux의 경우 시스템 의존성 추가 설치
agent-browser setup --with-deps
핵심 개념
1. 스냅샷 + Ref 워크플로우
agent-browser의 핵심은 **접근성 트리(Accessibility Tree)**와 ref 시스템입니다.
# 1. 페이지 열기
agent-browser open https://example.com
# 2. 접근성 스냅샷 가져오기 (ref 포함)
agent-browser snapshot -i
# 출력:
# - heading "Example Domain" [ref=e1] [level=1]
# - button "Submit" [ref=e2]
# - textbox "Email" [ref=e3]
# - link "Learn more" [ref=e4]
# 3. ref를 사용하여 요소와 상호작용
agent-browser click @e2 # 버튼 클릭
agent-browser fill @e3 "[email protected]" # 텍스트 입력
agent-browser text @e1 # 텍스트 가져오기
2. 스냅샷 옵션
# 전체 접근성 트리
agent-browser snapshot
# 인터랙티브 요소만 (버튼, 입력, 링크)
agent-browser snapshot -i
# 컴팩트 모드 (빈 구조 요소 제거)
agent-browser snapshot -c
# 깊이 제한
agent-browser snapshot -d 3
# CSS 선택자로 범위 제한
agent-browser snapshot -s "#main"
# 옵션 조합
agent-browser snapshot -i -c -d 5
3. JSON 모드 (AI 에이전트용)
# JSON 출력으로 파싱 가능한 결과 반환
agent-browser snapshot --json
# {"success":true,"data":{"snapshot":"...","refs":{"e1":{"role":"heading","name":"Title"},...}}}
E2E 테스트 패턴
패턴 1: 기본 페이지 테스트
#!/bin/bash
# test_homepage.sh
set -e # 에러 시 즉시 중단
# 페이지 열기
agent-browser open https://myapp.com
# 페이지 타이틀 확인
TITLE=$(agent-browser title)
if [[ "$TITLE" != "My App" ]]; then
echo "FAIL: Expected title 'My App', got '$TITLE'"
exit 1
fi
# 주요 요소 존재 확인
agent-browser snapshot -i | grep -q "button.*Login" || {
echo "FAIL: Login button not found"
exit 1
}
echo "PASS: Homepage test"
agent-browser close
패턴 2: 로그인 플로우 테스트
#!/bin/bash
# test_login.sh
set -e
# 로그인 페이지 열기
agent-browser open https://myapp.com/login
# 스냅샷으로 요소 ref 확인
agent-browser snapshot -i
# - textbox "Email" [ref=e1]
# - textbox "Password" [ref=e2]
# - button "Sign In" [ref=e3]
# 이메일 입력
agent-browser fill @e1 "[email protected]"
# 비밀번호 입력
agent-browser fill @e2 "password123"
# 로그인 버튼 클릭
agent-browser click @e3
# URL 변경 대기
agent-browser wait url "**/dashboard"
# 대시보드 확인
URL=$(agent-browser url)
if [[ "$URL" != *"dashboard"* ]]; then
echo "FAIL: Not redirected to dashboard"
exit 1
fi
echo "PASS: Login flow"
agent-browser close
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 645 lines · 113 tokens per session scan A 56c76b5c9d8e
e2e-agent-browser is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 113 tokens to every session and 3,596 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具,支持所有主流浏览器的无头/有头自动化操作,包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.