Summary
This is browser automation built specifically for AI agents to control through CLI commands. The workflow is clean: open a URL, snapshot to get element references like @e1 and @e2, then interact using those refs to click, fill forms, or extract data. It handles the stuff you'd expect like screenshots, PDF generation, and state persistence for login sessions, plus some nice touches like connecting to an existing Chrome instance or running tests on iOS Simulator. The ref-based interaction model is smart because it sidesteps the usual brittleness of CSS selectors. If you're building agents that need to interact with websites programmatically, this gives you the primitives without forcing you into a heavier framework.
Install to Claude Code
npx -y skills add countbot-ai/countbot --skill agent-browser --agent claude-codeInstalls into .claude/skills of the current project.
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Files
SKILL.md
Select a file.
Featured
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →First SeenJun 11, 2026
