Claude MarketplacesSubmit
eyadsibai avatar

Agent Browser

eyadsibai/ltk

If you're automating browsers through Claude's CLI and want something simpler than Playwright, this wraps Vercel's headless browser tool with a snapshot and ref pattern that works well for AI. You navigate to a page, run snapshot to get interactive elements tagged as @e1, @e2, etc., then use those refs to click, fill forms, or scrape. It handles the common stuff like screenshots, PDFs, and waiting for elements. The workflow is straightforward: snapshot after each navigation to get fresh refs, then act on them. Good for bash-based automation where you want readable commands instead of diving into full browser testing frameworks.

skills.sh installs
166
GitHub stars
7
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add eyadsibai/ltk --skill agent-browser --agent claude-code

Installs into .claude/skills of the current project.

Files

agent-browser: CLI Browser Automation

Vercel's headless browser automation CLI designed for AI agents. Uses ref-based selection (@e1, @e2) from accessibility snapshots.

Setup

# Check installation
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"

# Install if needed
npm install -g agent-browser
agent-browser install  # Downloads Chromium

Core Workflow

The snapshot + ref pattern is optimal for LLMs:

  1. Navigate to URL
  2. Snapshot to get interactive elements with refs
  3. Interact using refs (@e1, @e2, etc.)
  4. Re-snapshot after navigation or DOM changes
agent-browser open https://example.com
agent-browser snapshot -i          # Get refs
agent-browser click @e1            # Use ref
agent-browser fill @e2 "text"
agent-browser snapshot -i          # Re-snapshot

Key Commands

Navigation

agent-browser open <url>       # Navigate to URL
agent-browser back             # Go back
agent-browser forward          # Go forward
agent-browser reload           # Reload page
agent-browser close            # Close browser

Snapshots (Essential for AI)

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/eyadsibai/ltk
Categories
AI & Agent Building, Automation & Workflows, Cloud & Infrastructure, CLI & Terminal
First seen
Jun 3, 2026

More from eyadsibai/ltk

All 6

Recommended

More AI & Agent Building
1google-labs-code avataragent-dx-cli-scalegoogle-labs-code/design.mdA scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.166skills.sh installs
2qodex-ai avatardata-organization-systemqodex-ai/ai-agent-skillsOrganize and categorize files into logical structures. Creates folder hierarchies, renames files systematically, and consolidates related data.166skills.sh installs
3sickn33 avataragent-orchestratorsickn33/antigravity-awesome-skillsagent orchestrator166skills.sh installs
4sickn33 avataravoid-ai-writingsickn33/antigravity-awesome-skillsavoid ai writing165skills.sh installs
5wwwzhouhui avatarjimeng_mcp_skillwwwzhouhui/skills_collection使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。165skills.sh installs
6akillness avatarprompt-repetitionakillness/oh-my-skillsprompt repetition164skills.sh installs