browser-benchmark

Community

Benchmark browser automation for cheaper tokens.

Authorleonardoacosta
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmarks browser automation token costs to reveal efficiency gaps between tools, helping teams minimize token usage and runtime costs.

Core Features & Use Cases

  • Compare token costs between agent-browser and Playwright MCP across a curated set of test pages.
  • Produce structured results for analysis and reporting, enabling process optimizations.
  • Use cases include evaluating tool efficiency during browser automation tasks, cost-modeling, and regression checks.

Quick Start

Run the benchmark across several test pages to compare token costs between agent-browser and Playwright MCP.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: browser-benchmark
Download link: https://github.com/leonardoacosta/central-claude/archive/main.zip#browser-benchmark

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.