trinhhaox/ag-kit/browser-automation
Claude Code and agent skill by trinhhaox/ag-kit
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Persistent Playwright browser daemon for QA testing, web interaction, and screenshots. Sub-200ms command latency via HTTP API.
Install
npx vskill@latest install trinhhaox/ag-kit/browser-automationSKILL.md
Browser Automation
Persistent Playwright browser daemon with element ref system for fast, reliable web interaction.
Runtime Scripts
| Script | Purpose | Usage | |
|---|---|---|---|
scripts/browser-daemon.py | Start browser server | python scripts/browser-daemon.py [--port 9222] | |
scripts/browser-cli.py | Send commands to daemon | python scripts/browser-cli.py <command> [args...] |
Requires: pip install playwright && playwright install chromium
Quick Start
API Endpoints
| Method | Path | Body | Response | |
|---|---|---|---|---|
| POST | /navigate | {"url": "..."} | {"title": "...", "url": "..."} | |
| POST | /click | {"ref": "@e1"} | {"ok": true} | |
| POST | /type | {"ref": "@e2", "text": "..."} | {"ok": true} | |
| POST | /screenshot | {"full_page": false} | {"image": "base64..."} | |
| POST | /evaluate | {"script": "document.title"} | {"result": "..."} | |
| POST | /wait | {"ref": "@e1", "timeout": 5000} | {"ok": true} | |
| GET | /refs | — | {"refs": {"@e1": {...}, ...}} | |
| GET | /status | — | {"url": "...", "title": "...", "refs_count": N} | |
| POST | /stop | — | Graceful shutdown |
Ref System
Elements are addressed by refs (@e1, @e2, ...) built from the accessibility tree. See references/ref-system.md for details.
Key rules:
- Refs auto-clear on navigation
- Refs rebuild after each command that changes the page
- Use
refscommand to see current mapping - Refs use Playwright locators internally — no CSS selectors needed
Security
- Localhost-only binding (127.0.0.1)
- UUID bearer token per session (stored in /tmp/ag-browser-token)
- 30 min idle auto-shutdown
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/browser-automation/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/trinhhaox/ag-kit/browser-automation)