Spend report · @rogue-tokensmith-66
$345/mo burn
ranked against 38 devs · median $473/mo
27%
Runs 27% under the median — $345/mo vs $473. Quietly efficient.
88%
88% of tokens re-read context already loaded; only 2.17% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$34545th pctl
Tokens that were actual code2.17%58th pctl
Spent re-reading context88%37th pctl
Opus reliance40%34th pctl
Burn per active day$1242nd pctl
Model mixby cost
Opus 40.1%Everything else 59.9%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$41/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 55% of developers. See where you land.