Skills
.Work. You
Rest

agent-comparison

Community

Compare agent variants with evidence-driven benchmarks.

Software Engineering#agent#comparison#benchmark#code-quality#token-cost#race-detection#ab-test
Authornotque
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a structured approach to compare agent variants through controlled benchmarks, quantifying quality and total session token cost to guide production decisions.

Core Features & Use Cases

  • Systematically compare agent variants through controlled benchmarks
  • Measure total session token cost (prompt, reasoning, tools, retries)
  • Generate evidence-backed reports, highlighting production-impacting differences and bugs

Quick Start

Run the four phases in order (Prepare, Benchmark, Grade, and Report) using identical prompts to evaluate both agent variants.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: agent-comparison
Download link: https://github.com/notque/claude-code-toolkit/archive/main.zip#agent-comparison

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.