Spend report · @zen-compactor-72
$183/mo burn
ranked against 38 devs · median $473/mo
61%
Runs 61% under the median — $183/mo vs $473. Quietly efficient.
91%
91% of tokens re-read context already loaded; only 0.67% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$18329th pctl
Tokens that were actual code0.67%18th pctl
Spent re-reading context91%66th pctl
Opus reliance37%29th pctl
Burn per active day$626th pctl
Model mixby cost
Opus 37.3%Everything else 62.7%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$22/mo
/compact at natural breakpoints, /clear between tasks, trim CLAUDE.md — every turn re-reads it.
Cohort distributionprojected / month
<$100
5
$100–300
you
$300–600
7
$600–1k
5
$1k–2k
5
$2k–5k
3
$5k+
2
$ npx tokenrot
Leaner than 71% of developers. See where you land.