Spend report · @cracked-promptsmith-14

$604/mo burn

ranked against 38 devs · median $473/mo

1.3×
Burns 1.3× the median dev — $604/mo vs $473. Top 39% of the board.
93%
93% of tokens re-read context already loaded; only 1.53% was newly written code. Paying to reload, not to create.
Where this landspercentile vs cohort · ◆ median
Monthly spend$60461st pctl
Tokens that were actual code1.53%42nd pctl
Spent re-reading context93%76th pctl
Opus reliance45%45th pctl
Burn per active day$2058th pctl
Model mixby cost
Opus 44.9%Everything else 55.1%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$72/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 61% 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.