Compaction on Tokenise

Make Claude Code re-read your plan after every compaction: a SessionStart brief that also warns before a stale resume

Mon, 26 Oct 2026 07:10:00 +0000

Two hours into a refactor, the context window fills and Claude Code compacts. The summary is decent. It also says nothing about the decision you made at minute 20 not to add a dependency, and the next thing the agent does is propose adding one. Or you hit /clear between tasks, and the fresh session has no idea which branch it’s on, what’s uncommitted, or that a plan exists.

Claude Code now compacts your idle session before the cache expires. Here's when that saves money and when it costs you

Fri, 16 Oct 2026 11:03:00 +0000

You step away from a long Claude Code session for lunch. An hour and a bit later you type a one-line follow-up, and that single message reprocesses the whole conversation from scratch, because the one-hour prompt cache lapsed while you were gone. At 400,000 tokens of context on Sonnet 5.5, that one line costs about $1.60 before the model has said anything.

Claude Code waits until 967K tokens to compact. Pick the window yourself

Tue, 13 Oct 2026 11:05:00 +0000

A Sonnet 5.5 session that has been running since the morning stand-up is probably carrying several hundred thousand tokens of old file reads, test output and abandoned approaches. Claude Code won’t touch that history until it nears the model’s limit. For models with a native 1M window, Anthropic’s docs put the default compaction point at about 967K tokens.