prompt-caching
Installation
SKILL.md
Prompt Caching
Cache LLM prompt prefixes for 90% token savings.
Supported Models (2026)
| Provider | Models |
|---|---|
| Claude | Opus 4.1, Opus 4, Sonnet 4.5, Sonnet 4, Sonnet 3.7, Haiku 4.5, Haiku 3.5, Haiku 3 |
| OpenAI | gpt-5.2, gpt-5.2-mini, o3, o3-mini (automatic caching) |