prompt-cache

Community

Cache-driven prompt design for repeatable LLM dispatch.

Authorbrucebanner010198-commits
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Reduces redundant prompt processing and compute costs by explicitly caching stable portions of multi-turn dispatch prompts and associated telemetry data, improving latency and predictability in large prompt pipelines.

Core Features & Use Cases

  • Breakpoint-driven assembly: fix four deterministic cache breakpoints (system prompt, root AGENTS.md, council AGENTS.md, and skill SKILL.md) to maximize cache hit potential.
  • TTL and telemetry policy: explicit TTL choices, per-project telemetry, and observability to monitor cache effectiveness and savings.
  • Workspace isolation and invalidation: safe cache invalidation when source prompts change to prevent cross-project bleed.
  • Use Case: accelerate repeated prompts across long-running dispatch workflows with stable content.

Quick Start

Initialize prompt-cache with a plan that declares breakpoints, TTL, and telemetry endpoints, then enable caching for repeated prompts to observe savings.

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: prompt-cache
Download link: https://github.com/brucebanner010198-commits/DevSecOps-Agency/archive/main.zip#prompt-cache

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.