Spend report · @budget-promptsmith-3
$310/mo burn
ranked against 38 devs · median $473/mo
34%
Runs 34% under the median — $310/mo vs $473. Quietly efficient.
86%
86% of tokens re-read context already loaded; only 2.87% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$31042nd pctl
Tokens that were actual code2.87%74th pctl
Spent re-reading context86%16th pctl
Opus reliance21%3rd pctl
Burn per active day$1039th pctl
Model mixby cost
Opus 21%Everything else 79%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$37/mo
/compact at natural breakpoints, /clear between tasks, trim CLAUDE.md — every turn re-reads it.
Cohort distributionprojected / month
<$100
5
$100–300
11
$300–600
you
$600–1k
5
$1k–2k
5
$2k–5k
3
$5k+
2
$ npx tokenrot
Leaner than 58% of developers. See where you land.