> demo crew · generated data · sign in to start yours
> percentages compare against the 3 days before this window
this week · ratios of the counted totals
of the context Claude Code sent was read back from the cache instead of sent fresh
> output this week: about 6.9 novels of text (621K words, estimated at 0.75 words per token and 90K words a novel)
last 52 weeks · Monday to Sunday
this week
share of output tokens per model family · last 26 weeks
this week · the reasoning effort each reply ran at
61% of replies
| level | output per reply |
|---|---|
| not set | 637 |
| low | 534 |
| medium | 511 |
this week · tokens that ran in subagents (Task, agents) rather than your conversation
161 of 1,632 replies in subagents
this week · replies per block of your computer's own clock · afternoon person
this week · cache reads are context Claude Code sent again
output tokens this week by model
Claude Code replies per day · older half on top, newer half below
| high | 501 |
| xhigh | 515 |
average Claude Code replies per weekday this week
> weeks run Monday to Sunday · all time · messages and tool calls count from CLI 0.7.0
