openclaw-token-optimizer

Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling prompt caching, heartbeat, context pruning, compaction, memory search or qmd, subagents, model tiering, and cron frequency. Use when a user asks to reduce OpenClaw token spend, speed up sessions, shrink context, or configure openclaw.json and memory search settings.