Spend report · @budget-promptsmith-36

$152/mo burn

ranked against 38 devs · median $473/mo

68%
Runs 68% under the median$152/mo vs $473. Quietly efficient.
93%
93% of tokens re-read context already loaded; only 3.07% was newly written code. Paying to reload, not to create.
91%
Opus drives 91% of the bill — the single biggest cost lever on this profile.
Where this landspercentile vs cohort · ◆ median
Monthly spend$15218th pctl
Tokens that were actual code3.07%84th pctl
Spent re-reading context93%71st pctl
Opus reliance91%79th pctl
Burn per active day$516th pctl
Model mixby cost
Opus 90.6%Everything else 9.4%
Cut the burncomputed from these numbers
Route routine work to Sonnet — saves ~$33/mo
Keep Opus for architecture and hard debugging; /model sonnet for edits, tests, boilerplate.
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 82% 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.