Spend report · @overclocked-contexthoarder-44
$70/mo burn
ranked against 38 devs · median $473/mo
85%
Runs 85% under the median — $70/mo vs $473. Quietly efficient.
95%
95% of tokens re-read context already loaded; only 2.01% was newly written code. Paying to reload, not to create.
▲
Last 3 days ran 2.43× the personal norm — the signature of a runaway loop or caching bug.
Where this landspercentile vs cohort · ◆ median
Monthly spend$703rd pctl
Tokens that were actual code2.01%55th pctl
Spent re-reading context95%84th pctl
Opus reliance20%1st pctl
Burn per active day$21st pctl
Model mixby cost
Opus 20.3%Everything else 79.7%
Cut the burncomputed from these numbers
Cut context re-reads — saves ~$8/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
you
$100–300
11
$300–600
7
$600–1k
5
$1k–2k
5
$2k–5k
3
$5k+
2
$ npx tokenrot
Leaner than 97% of developers. See where you land.