Spend report · @sleepless-contexthoarder-12
$73/mo burn
ranked against 38 devs · median $473/mo
85%
Runs 85% under the median — $73/mo vs $473. Quietly efficient.
92%
92% of tokens re-read context already loaded; only 2.92% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$735th pctl
Tokens that were actual code2.92%76th pctl
Spent re-reading context92%68th pctl
Opus reliance31%18th pctl
Burn per active day$23rd pctl
Model mixby cost
Opus 31.3%Everything else 68.7%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$9/mo
/compact at natural breakpoints, /clear between tasks, trim CLAUDE.md — every turn re-reads it.
Cohort distributionprojected / month
<$100
you
$100–300
11
$300–600
7
$600–1k
5
$1k–2k
5
$2k–5k
3
$5k+
2
$ npx tokenrot
Leaner than 95% of developers. See where you land.