<skill-slug>
01Skill Claude CodeCodex
One-line description of what this fix does and why it matters.
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.
Skill Claude CodeCodex
One-line description of what this fix does and why it matters.
Skill Claude CodeCodex
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
Skill Claude CodeCodex
Aider's --cache-prompts is off by default. Flip it on for supported models.
Skill Claude CodeCodex
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
Skill Claude CodeCodex
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
Skill Claude CodeCodex
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
Skill Claude CodeCodex
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
Skill Claude CodeCodex
Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.
Skill Claude CodeCodex
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
Skill Claude CodeCodex
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.
Skill Claude CodeCodex
OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.
Skill Claude CodeCodex
OpenCode doesn't set promptcachekey for Mistral models, missing the documented 10% cached-token discount.
Skill Claude CodeCodex
Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.
Skill Claude CodeCodex
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: