Context Compressor

Compresses large context before reasoning to save tokens while keeping the evidence you need to answer correctly. Runs locally via Python scripts, no MCP server required. You get three modes: baseline for generic compression, query_guided when you have a specific question, and evidence_aware when correctness matters and you want an explicit sufficiency check. The skill auto-triggers at 80K tokens and blocks new agent spawns at 150K until you compress. Best for chunky RAG payloads, massive codebases, or long chat histories where you're burning tokens on repeated context. The evidence validation is honest: if compressed output looks too thin, it tells you instead of guessing.