←back to thread

186 points syntax-sherlock | 3 comments | | HN request time: 0s | source

I got tired of playwright-mcp eating through Claude's 200K token limit, so I built this using the new Claude Skills system. Built it with Claude Code itself.

Instead of sending accessibility tree snapshots on every action, Claude just writes Playwright code and runs it. You get back screenshots and console output. That's it.

314 lines of instructions vs a persistent MCP server. Full API docs only load if Claude needs them.

Same browser automation, way less overhead. Works as a Claude Code plugin or manual install.

Token limit issue: https://github.com/microsoft/playwright-mcp/issues/889

Claude Skills docs: https://docs.claude.com/en/docs/claude-code/skills

Show context
AftHurrahWinch ◴[] No.45644100[source]
MCPs are deterministic, SKILLS.md isn't. Also run.js can run arbitrarily generated Node.js code. It is a trivial vector for command injection.

This might be sufficient for an independent contractor or student. It shouldn't be used in a production agent.

replies(4): >>45644151 #>>45644797 #>>45645147 #>>45645225 #
1. syntax-sherlock ◴[] No.45644151[source]
Yeah, this isn’t meant to replace your real tests it’s more for quick “does my new feature work?” checks during local dev. Think of it like scriptable manual testing: Claude spits out the Playwright code faster than you would, but it’s not CI-level coverage.

And for privacy screenshots stay local in /tmp, but console output and page content do go to Claude/Anthropic. It’s designed for dev environments with dummy data, not prod. Same deal as using Claude for any coding help.

replies(2): >>45644629 #>>45661527 #
2. pacoWebConsult ◴[] No.45644629[source]
If you're going to use claude to help you respond to feedback the least you can do is restate this in your own words. Parent commenter deserves the respect of corresponding with a real human being.
3. blks ◴[] No.45661527[source]
You don’t understand what you’re talking about enough so you have to ask llm to generate a response for you?