token-saver-context-compression

Use this skill to reduce token usage while preserving grounded evidence. This integrates:

Do not persist compressed content directly to memory files from a subprocess. Emit MemoryRecord payloads and let framework hooks process sync/indexing.

Use pnpm search:tokens to decide when to invoke this skill:

Agent-studio 的搜尋感知上下文壓縮工作流程。使用 pnpm 混合搜尋 + token-saver 壓縮，然後透過 MemoryRecord 保留精煉的學習內容。 來源：oimiragieo/agent-studio。