Token Saver Context Compression

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

• pnpm search:code (hybrid retrieval)
• token-saver Python compression scripts
• MemoryRecord persistence into framework memory
• spawn prompt evidence injection ([mem:*] / [rag:*])

Activation

The token-saver skill can be invoked in two ways:

Manual Invocation (always available)

Skill({ skill: 'token-saver-context-compression' });