(github.com)

186 points syntax-sherlock | 1 comments | 20 Oct 25 11:58 UTC | 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 ◴[20 Oct 25 14:08 UTC] No.45644100[source]▶

>>45642911 (OP) #

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. bravura ◴[20 Oct 25 15:07 UTC] No.45644797[source]▶

>>45644100 #

LLMs are not deterministic though. So by definition MCPs are not deterministic.

For example, GPT-5 doesn't support temperature parameter. And even models that do support temperature are not deterministic with temperature=0.

↑

Show HN: Playwright Skill for Claude Code – Less context than playwright-MCP