Spend report · @overclocked-cachegoblin-22

$13,990/mo burn

ranked against 38 devs · median $473/mo

29.6×
Burns 29.6× the median dev — $13,990/mo vs $473. Top 3% of the board.
96%
96% of tokens re-read context already loaded; only 0.35% was newly written code. Paying to reload, not to create.
96%
Opus drives 96% of the bill — the single biggest cost lever on this profile.
Where this landspercentile vs cohort · ◆ median
Monthly spend$13,99097th pctl
Tokens that were actual code0.35%5th pctl
Spent re-reading context96%92nd pctl
Opus reliance96%95th pctl
Burn per active day$72797th pctl
Model mixby cost
Opus 96.4%Everything else 3.6%
Cut the burncomputed from these numbers
Route routine work to Sonnet — saves ~$3,237/mo
Keep Opus for architecture and hard debugging; /model sonnet for edits, tests, boilerplate.
Cut context re-reads — saves ~$1,679/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 5
$1k–2k 5
$2k–5k 3
$5k+ you
$ npx tokenrot
Out-burns 97% 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.