Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

fix: use correct unscoped agent-browser package name (#77)

Jeff Scott Ward56ff5d444bfe
diff --git a/agents/e2e-runner.md b/agents/e2e-runner.md
index 4990461bb..4f8ffab57 100644
--- a/agents/e2e-runner.md
+++ b/agents/e2e-runner.md
@@ -21,34 +21,72 @@ You are an expert end-to-end testing specialist. Your mission is to ensure criti
### Agent Browser Setup
```bash
-# Install agent-browser
-npm install @anthropic-ai/agent-browser
-# or
-pnpm add @anthropic-ai/agent-browser
+# Install agent-browser globally
+npm install -g agent-browser
+
+# Install Chromium (required)
+agent-browser install
+```
+
+### Agent Browser CLI Usage (Primary)
+
+Agent Browser uses a snapshot + refs system optimized for AI agents:
+
+```bash
+# Open a page and get a snapshot with interactive elements
+agent-browser open https://example.com
+agent-browser snapshot -i # Returns elements with refs like [ref=e1]
+
+# Interact using element references from snapshot
+agent-browser click @e1 # Click element by ref
+agent-browser fill @e2 "[email protected]" # Fill input by ref
+agent-browser fill @e3 "password123" # Fill password field
+agent-browser click @e4 # Click submit button
+
+# Wait for conditions
+agent-browser wait visible @e5 # Wait for element
+agent-browser wait navigation # Wait for page load
+
+# Take screenshots
+agent-browser screenshot after-login.png
+
+# Get text content
+agent-browser get text @e1
```
-### Agent Browser Usage
+### Agent Browser in Scripts
+
+For programmatic control, use the CLI via shell commands:
+
```typescript
-import { AgentBrowser } from '@anthropic-ai/agent-browser'
+import { execSync } from 'child_process'
-const browser = new AgentBrowser()
+// Execute agent-browser commands
+const snapshot = execSync('agent-browser snapshot -i --json').toString()
+const elements = JSON.parse(snapshot)
-// Semantic navigation - describe what you want
-await browser.navigate('https://example.com')
-await browser.click('the login button')
-await browser.fill('email input', '[email protected]')
-await browser.fill('password field', 'securepassword')
-await browser.click('submit button')
+// Find element ref and interact
+execSync('agent-browser click @e1')
+execSync('agent-browser fill @e2 "[email protected]"')
+```
+
+### Programmatic API (Advanced)
-// Wait for semantic conditions
-await browser.waitFor('dashboard to load')
-await browser.waitFor('user avatar to appear')
+For direct browser control (screencasts, low-level events):
+
+```typescript
+import { BrowserManager } from 'agent-browser'
+
+const browser = new BrowserManager()
+await browser.launch({ headless: true })
+await browser.navigate('https://example.com')
-// Take screenshots
-await browser.screenshot('after-login.png')
+// Low-level event injection
+await browser.injectMouseEvent({ type: 'mousePressed', x: 100, y: 200, button: 'left' })
+await browser.injectKeyboardEvent({ type: 'keyDown', key: 'Enter', code: 'Enter' })
-// Extract data semantically
-const username = await browser.getText('the username in the header')
+// Screencast for AI vision
+await browser.startScreencast() // Stream viewport frames
```
### Agent Browser with Claude Code