USAGE SOURCEBundled demo profiledeterministic full-profile data

EXPECTED MONTHLY PROVIDER BILL$21,848.47after $743.88 of assumed local savings$1,151.53 leftThis plan leaves almost no room for a spike.broad confidence · 30/30 days observedTune assumptions

MONTHLY AI COST PLAN

This demo pace lands near $22,592.35 in monthly paid AI spend.

That estimate extends 30 observed calendar days across a 30-day month. 0 days are still outside the evidence window, so confidence is broad. Nothing on this page changes usage, providers, score, or rank.

01 · OBSERVED$22,592.3530 calendar days · 30 active · 0 idle

02 · CALENDAR PACE$753.08 / day2026-06-02 → 2026-07-01

03 · 30-DAY PLAN$22,592.35$22,592.35 ÷ 30 days × 30

demo not account data19,700 accepted rows11 providers30 calendar days observed

OPERATOR BRIEF · READ THIS FIRST

The decision, without the dashboard jargon

observed $22,592.35 → projected $22,592.35 → planned $21,848.47

Budget status$1,151.53 left

95% of the $23,000.00 limit. One heavy day can erase the buffer.

Forecast confidencebroad · 30/30 days

0 days are unobserved. The current pace is extended 1.0×.

Review firstcodex-cli

Highest observed spend. That makes it the first place to inspect, not proof that it is wasteful.

Do nextCreate a real buffer

Review codex-cli jobs first, then lower paid usage or choose a limit you can enforce.

Plain English. We saw $22,592.35 across 30 calendar days, extended that pace to a 30-day estimate of $22,592.35, then subtracted $743.88 for the 35% local-work scenario. The result is $21,848.47 of estimated paid-provider spend against a $23,000.00 limit.

Expected bill$21,848.47

Monthly limit$23,000.00

EVIDENCE APERTUREbroad confidence

Coverage: 100%
Projection stretch: 1.0×
+10% local: −$212.54

Read: At least 21 calendar days are represented, so the pace includes a broad mix of active and idle time. 0 of 30 calendar days are outside the evidence window. The same-rhythm projection stretches the observed pace 1.0×. Even at 100% of eligible work moved local, the scenario floor is $20,466.99.

CHANGE THE ASSUMPTIONS

Choose your comfort level

Updates instantly

Monthly spending limitThe most you are comfortable paying for AI providers in one month.$23,000.00Eligible work moved localA scenario for repeat work that could run on local tools instead of paid providers.35% → save $743.88

This percentage applies only to $2,125.36 of estimated eligible work, not to the full $22,592.35 forecast.

OPERATOR METHODCalculation & confidence ledger

Open six calculation rows, provider review, evidence boundaries, formula, and CLI dry run.

READ THE CALCULATION

Where the result comes from

Observed source period30 calendar days · 30 active · 0 idle$22,592.35
Same-rhythm 30-day projection$22,592.35 ÷ 30 days × 30$22,592.35
Estimated local savings35% of eligible work−$743.88
Planned paid spendForecast after this scenario$21,848.47
Your monthly limitThe boundary you selected$23,000.00
Budget remainingclose to the limit$1,151.53

WHERE TO REVIEW FIRSTcodex-cli

It has the highest observed spend in this example. That does not mean it is wasteful; check its high-cost jobs before changing providers.

CONFIDENCE BOUNDARY

What is known, estimated, and unchanged

Known from the demo$22,592.35 observed across 30 calendar days · 30 active · 0 idle, plus provider totals and accepted rows.

Estimated hereThe 30-day projection assumes the same calendar rhythm. Local savings are a separate scenario. Either can be wrong if work changes.

Never changed hereUsage totals, provider settings, public profile, score, and rank. This page writes nothing.

Show the formula and CLI dry run

$22,592.35 ÷ 30 × 30 − ($2,125.36 × 35%) = $21,848.47

npx vibetrack mission --budget 23000Preview only. The command retains --dry-run.