You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
UsageArea: what it touches
ImprovementsKind: in v2.1.299,
ImprovementsSection of the release
What
Claude Code's usage breakdown, which shows what your usage went on, now tracks and comments on four more things:
Max effort: the share of your usage spent at the max effort level
Workflows: the share spent on workflows, which split a task across many agents that each send their own requests
Always-on context over 40k tokens: the share spent on context loaded at the start of every request, when it is larger than 40,000 tokens (a token is a small chunk of text)
Tool results over 10k tokens: the share spent on outputs from tools that are larger than 10,000 tokens
Each has its own headline and a piece of advice, pointing to /effort to change the effort level or /context to see what is filling the context.
Why
You get specific pointers on what is driving your usage and which command to reach for to bring it down.
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's release notes agreeAdded /effort and /fast in agent view to set what new sessions start with; a bare /model, /effort or /fast there now opens a picker
