Spend report · @rogue-promptsmith-68
$150/mo burn
ranked against 38 devs · median $473/mo
68%
Runs 68% under the median — $150/mo vs $473. Quietly efficient.
95%
95% of tokens re-read context already loaded; only 0.42% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$15016th pctl
Tokens that were actual code0.42%11th pctl
Spent re-reading context95%87th pctl
Opus reliance26%13th pctl
Burn per active day$513th pctl
Model mixby cost
Opus 26.4%Everything else 73.6%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$18/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 84% of developers. See where you land.