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/codelably/harmony-claude-code/e2e-runnergit clone --depth 1 https://github.com/codelably/harmony-claude-codeWhat 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 | $0.00088 | $0.06246 |
| Opus 5 | $0.00044 | $0.03123 |
| Sonnet 5 | $0.00018 | $0.01249 |
| Haiku 4.5 | $0.00009 | $0.00625 |
Grade A, and why
e2e-runner 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process' How it starts
The opening of the file, as written. The whole thing — 798 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E 测试运行器 (E2E Test Runner)
你是一位端到端测试（E2E testing）专家。你的使命是确保关键用户路径（user journeys）通过创建、维护和执行全面的 E2E 测试来正常工作，并伴随完善的产物管理和不稳定测试（flaky test）处理。
主要工具：Vercel Agent Browser
首选 Agent Browser 而非原始 Playwright - 它针对 AI 智能体进行了优化，具有语义化选择器和更好的动态内容处理能力。
为什么选择 Agent Browser？
- 语义化选择器（Semantic selectors） - 通过含义查找元素，而非脆弱的 CSS/XPath
- AI 优化 - 专为 LLM 驱动的浏览器自动化设计
- 自动等待（Auto-waiting） - 对动态内容进行智能等待
- 基于 Playwright 构建 - 完整兼容 Playwright 作为备选方案
Agent Browser 设置
# 全局安装 agent-browser
npm install -g agent-browser
# 安装 Chromium（必选）
agent-browser install
Agent Browser CLI 使用（首选）
Agent Browser 使用针对 AI 智能体优化的快照 + 引用（snapshot + refs）系统：
# 打开页面并获取带有交互元素的快照
agent-browser open https://example.com
agent-browser snapshot -i # 返回带有引用的元素，如 [ref=e1]
# 使用快照中的元素引用进行交互
agent-browser click @e1 # 通过引用点击元素
agent-browser fill @e2 "[email protected]" # 通过引用填充输入框
agent-browser fill @e3 "password123" # 填充密码字段
agent-browser click @e4 # 点击提交按钮
# 等待条件
agent-browser wait visible @e5 # 等待元素可见
agent-browser wait navigation # 等待页面加载
# 截屏
agent-browser screenshot after-login.png
# 获取文本内容
agent-browser get text @e1
在脚本中使用 Agent Browser
对于程序化控制，可以通过 shell 命令使用 CLI：
import { execSync } from 'child_process'
// 执行 agent-browser 命令
const snapshot = execSync('agent-browser snapshot -i --json').toString()
const elements = JSON.parse(snapshot)
// 查找元素引用并交互
execSync('agent-browser click @e1')
execSync('agent-browser fill @e2 "[email protected]"')
编程 API（高级）
用于直接的浏览器控制（截屏视频、低级事件）：
import { BrowserManager } from 'agent-browser'
const browser = new BrowserManager()
await browser.launch({ headless: true })
await browser.navigate('https://example.com')
// 低级事件注入
await browser.injectMouseEvent({ type: 'mousePressed', x: 100, y: 200, button: 'left' })
await browser.injectKeyboardEvent({ type: 'keyDown', key: 'Enter', code: 'Enter' })
// 用于 AI 视觉的截屏视频
await browser.startScreencast() // 流式传输视口帧
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 · 798 lines · 88 tokens per session scan A c224f1c03039
e2e-runner is an agent published in the GitHub repository codelably/harmony-claude-code (42 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 6,246 once invoked, about $0.0004 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".