agent-runtime-cache-benchmark

Official

Benchmark prompt-cache reuse and failures.

AuthorPrompthon-IO
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Benchmark and explain prompt-cache reuse by comparing two agent-run artifacts (cold vs warm) to determine whether caching improves performance and where it may break.

Core Features & Use Cases

  • Compare two structured run artifacts to quantify cache hits, latency delta, and hash stability.
  • Identify likely cache-break events when system prompts, tool manifests, or history change between runs.
  • Produce a concise local Markdown or JSON report for operator review.

Quick Start

Collect two JSON run artifacts (cold and warm) and run the helper to generate the report.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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-runtime-cache-benchmark
Download link: https://github.com/Prompthon-IO/agent-systems-handbook/archive/main.zip#agent-runtime-cache-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.