Context Optimization

This is about squeezing more out of Claude's context window without upgrading to a bigger model. It walks through four strategies in priority order: KV-cache optimization (reordering prompts so the engine reuses cached tensors), then compression, masking, and partitioning. The author claims you can double or triple effective capacity if you're disciplined about it. Use this when you're hitting context limits, trying to cut costs on long conversations, or building production agent systems that need to handle large documents. The emphasis on applying techniques in risk order (zero-risk caching first, riskier compression later) is smart. Originally from shipshitdev's library, now maintained by flora131 with solid security audit coverage.