Summary
A hardened fork of agent-browser that wraps all the upstream commands (50+ for interaction, waiting, extraction, tabs, network) with URL blocklists, rate limiting, and robots.txt checks. You get the same React DevTools introspection, Core Web Vitals, semantic locators, and HAR capture from 0.27.0, but every operation goes through OrchestKit's safety layer first. Use this when you're automating browser workflows in shared environments or production contexts where you need guardrails against accidentally hammering external sites or ignoring crawl policies. The skill itself doesn't add commands, it just intercepts them. Command reference lives upstream in the base agent-browser skill.
Install to Claude Code
npx -y skills add yonatangross/orchestkit --skill browser-tools --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
