Spend report · @reckless-tokenlord-36

$126/mo burn

ranked against 38 devs · median $473/mo

73%
Runs 73% under the median$126/mo vs $473. Quietly efficient.
94%
94% of tokens re-read context already loaded; only 1.49% was newly written code. Paying to reload, not to create.
Last 3 days ran 1.92× the personal norm — the signature of a runaway loop or caching bug.
Where this landspercentile vs cohort · ◆ median
Monthly spend$12613th pctl
Tokens that were actual code1.49%39th pctl
Spent re-reading context94%82nd pctl
Opus reliance25%8th pctl
Burn per active day$411th pctl
Model mixby cost
Opus 24.8%Everything else 75.2%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$15/mo
/compact at natural breakpoints, /clear between tasks, trim CLAUDE.md — every turn re-reads it.
Audit the last 3 days for a runaway loop
A retrying agent quietly eats 10–100× a normal session.
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 87% 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.