Spend report · @budget-tokensmith-12

$737/mo burn

ranked against 38 devs · median $473/mo

1.6×
Burns 1.6× the median dev — $737/mo vs $473. Top 34% of the board.
91%
91% of tokens re-read context already loaded; only 1.38% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$73766th pctl
Tokens that were actual code1.38%34th pctl
Spent re-reading context91%61st pctl
Opus reliance40%32nd pctl
Burn per active day$2563rd pctl
Model mixby cost
Opus 40%Everything else 60%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$88/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 7
$600–1k you
$1k–2k 5
$2k–5k 3
$5k+ 2
$ npx tokenrot
Out-burns 66% of developers. See where you land.

The Burn Report

Once a month: what the cohort actually spent, which models got throttled, and where the money leaked. Written from the board's data — no spam, unsubscribe anytime.