> demo crew · generated data · sign in to start yours
> percentages compare against the 4 days before this window
this month · ratios of the counted totals
of the context Claude Code sent was read back from the cache instead of sent fresh
> output this month: about 2.9 novels of text (261.8K words, estimated at 0.75 words per token and 90K words a novel)
last 52 weeks · Monday to Sunday
this month
share of tokens per model family · last 26 weeks
this month · the reasoning effort each reply ran at
71% of replies
| level | output per reply |
|---|---|
| not set | 727 |
| low | 698 |
| medium | 657 |
| high | 689 |
this month · tokens that ran in subagents (Task, agents) rather than your conversation
27 of 522 replies in subagents
> counted since Nov 2026: earlier days were sent by a CLI before 0.7.0
this month · replies per block of your computer's own clock · early bird
> counted since Nov 2026: earlier days were sent by a CLI before 0.7.0
this month · cache reads are context Claude Code sent again
tokens this month by model
Claude Code replies per day · older half on top, newer half below
> counted since Nov 2026: earlier days were sent by a CLI before 0.7.0
average Claude Code replies per weekday this month
> weeks run Monday to Sunday · all time · messages and tool calls count from CLI 0.7.0
