session-bench

Community

Benchmark Claude Code sessions for token cost and efficiency.

Authorguyman-tr
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill allows users to measure and grade the cost and efficiency of Claude Code sessions, helping to identify improvements in context management and token usage.

Core Features & Use Cases

  • Session Benchmarking: Analyze the cost of a Claude Code session, including tokens used and context growth.
  • Comparison Against Baseline: Compare the performance of a session against a previously set baseline.
  • Efficiency Analysis: Evaluate the efficiency of a session and suggest improvements.

Quick Start

Measure the cost of your last session by running: python tools/session-bench/measure_session.py --save.

Dependency Matrix

Required Modules

python

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: session-bench
Download link: https://github.com/guyman-tr/Databricks_Knowledge/archive/main.zip#session-bench

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 620,000+ vetted skills library on demand.