Spend report · @stealth-promptsmith-5
$1,078/mo burn
ranked against 38 devs · median $473/mo
2.3×
Burns 2.3× the median dev — $1,078/mo vs $473. Top 26% of the board.
87%
87% of tokens re-read context already loaded; only 1.12% was newly written code. Paying to reload, not to create.
95%
Opus drives 95% of the bill — the single biggest cost lever on this profile.
Where this landspercentile vs cohort · ◆ median
Monthly spend$1,07874th pctl
Tokens that were actual code1.12%29th pctl
Spent re-reading context87%26th pctl
Opus reliance95%84th pctl
Burn per active day$3671st pctl
Model mixby cost
Opus 94.5%Everything else 5.5%
Cut the burncomputed from these numbers
Route routine work to Sonnet — saves ~$244/mo
Keep Opus for architecture and hard debugging; /model sonnet for edits, tests, boilerplate.
Cut context re-reads — saves ~$129/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
you
$2k–5k
3
$5k+
2
$ npx tokenrot
Out-burns 74% of developers. See where you land.