playbook-prompt-caching

playbook-prompt-caching

Practical playbook for maximizing prompt cache hit rate and minimizing token spend on LLM/agentic systems (Anthropic, OpenAI, Google Gemini, self-hosted vLLM). Covers prompt structure rules, multi-turn cache breakpoint placement, tool definition stability, dynamic content handling, TTL choice, multi-tenant isolation, and known anti-patterns.

Installation

# Copy this command into Claude Code to install this skill
/plugin add https://github.com/deniaud/agent-treasures-public/tree/main/claude/.claude/skills/playbook-prompt-caching

About

• Author: deniaud
• Stars: 3

For more information, visit the GitHub repository.