←back to thread

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

(github.com)
186 points syntax-sherlock | 2 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]▶
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. siva7 ◴[20 Oct 25 15:37 UTC] No.45645147[source]▶
MCPs aren't deterministic...
replies(1): >>45647134 #
2. AftHurrahWinch ◴[20 Oct 25 18:09 UTC] No.45647134[source]▶
Yes, they are. Like any standard API, it is an orchestration layer that, given a specific input should always execute the same logic and produce a consistent output. Its job is deterministic execution.

The agentic system that uses MCP (e.g., an LLM) is fundamentally non-deterministic. The LLM's decision of which tool to call, when to call it, and what to do with the response is stochastic.