Is the Mk Agent Browser skill free?

Yes. The skill itself is free from ngocsangyem/MeowKit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Mk Agent Browser SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Mk Agent Browser?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Mk Agent Browser with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Mk Agent Browser

Drives the agent-browser CLI for real Chrome automation with accessibility-tree refs and an auth vault.

by ngocsangyem · ngocsangyem/MeowKit

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 96a3312

Ran the real agent-browser CLI (npm i agent-browser) end to end against a local throwaway page: open, snapshot -i, click, and an eval confirmed the DOM actually mutated to 'clicked!' — the skill's own warning about refs going stale after navigation bit me mid-test exactly as documented.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Mk Agent Browser does

Wraps the vercel-labs agent-browser npm CLI (open/snapshot/click/fill/screenshot over real Chrome via CDP) with compact @eN accessibility-tree refs, session/auth-vault helpers, and an MCP server mode. Triggers on browser automation, QA/dogfooding, Electron, Slack-in-browser, and cloud-browser (Browserbase/AgentCore/Vercel Sandbox) tasks; explicitly defers to sibling skills for the user's real Chrome profile or reusable Playwright specs.

How to install Mk Agent Browser

git clone https://github.com/ngocsangyem/MeowKit
cd MeowKit
mkdir -p ~/.claude/skills
cp -r .claude/skills/agent-browser ~/.claude/skills/mk-agent-browser

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Mk Agent Browser

/mk-agent-browser Drives the agent-browser CLI for real Chrome automation with accessibility-tree refs and an auth vault.

It also activates on plain-language prompts like these:

Open this local page, click the button, and confirm the DOM updated
Automate Chrome with accessibility-tree refs to test this login flow
Drive real Chrome via CDP to snapshot and click through this page

Frequently asked questions

Is the Mk Agent Browser skill free?: Yes. The skill itself is free from ngocsangyem/MeowKit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Mk Agent Browser work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran the real agent-browser CLI (npm i agent-browser) end to end against a local throwaway page: open, snapshot -i, click, and an eval confirmed the DOM actually mutated to 'clicked!' — the skill's own warning about refs going stale after navigation bit me mid-test exactly as documented.
What is the Mk Agent Browser SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Mk Agent Browser?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Mk Agent Browser with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.