prompt-caching
✓Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
Installation
SKILL.md
| Claude | Opus 4.1, Opus 4, Sonnet 4.5, Sonnet 4, Sonnet 3.7, Haiku 4.5, Haiku 3.5, Haiku 3 | | OpenAI | gpt-4o, gpt-4o-mini, o1, o1-mini (automatic caching) |
| Min prefix size | 1,024 tokens (Claude) | | Breakpoint count | 2-4 per request | | Content order | Stable prefix first | | Default TTL | 5m for most cases | | Extended TTL | 1h if >10 reads/hour |
anthropic-caching Keywords: anthropic, claude, cachecontrol, ephemeral Solves:
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes. Source: yonatangross/skillforge-claude-plugin.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/yonatangross/skillforge-claude-plugin --skill prompt-caching- Category
- </>Dev Tools
- Verified
- ✓
- First Seen
- 2026-02-01
- Updated
- 2026-02-18
Quick answers
What is prompt-caching?
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes. Source: yonatangross/skillforge-claude-plugin.
How do I install prompt-caching?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/yonatangross/skillforge-claude-plugin --skill prompt-caching Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/yonatangross/skillforge-claude-plugin
Details
- Category
- </>Dev Tools
- Source
- skills.sh
- First Seen
- 2026-02-01