Plugin
prompt-cache-skills
Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
13 skills116
@onlyterpDrop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
@onlyterpAider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
@onlyterpAider's --cache-prompts is off by default. Flip it on for supported models.
@onlyterpLadder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune…
@onlyterpCline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.
@onlyterpCline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
@onlyterpContinue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
@onlyterp© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic