Pair Claude's memory tool with context editing for an 84% token cut on long-horizon tasks via a three-tier context

Claude Platform Docs·medium signal

Anthropic's memory tool (six commands over a persistent /memory directory) combined with context editing — the agent intentionally removing stale tool output and compressing its own working window — benchmarks at 84% token savings on long-running tasks. The pattern is a three-tier split: active context (current task state), a session scratchpad (intermediate reasoning/drafts), and persisted memory (structured notes written outside the window and pulled back later). Actionable: don't just append tool results — have the agent write structured notes to memory and actively evict stale context rather than paying to carry it.