Cut the waste, and prove it worked.
Earlyman ranks the fixes by what they would save, tests each one, and only counts a saving once its verdict is in.
Saved so far, verified
$4.20 a week
Nothing counts as saved until its verdict is in.
- FindPatterns that waste tokens, found in your own sessions.
- TestEach fix gets a baseline and a verdict date.
- Keep or roll backA change that did not help is rolled back.
How savings are tested. One fix at a time, against a baseline.
- 01Find the wasteEarlyman spots patterns that burn tokens in your own sessions, such as the same file read again and again.
- 02Test one fix at a timeEach fix starts with a baseline and a verdict date, so before and after can be compared fairly.
- 03Keep what workedA fix that saved money is kept. One that did not is rolled back, and nothing counts until the verdict is in.
Clear what needs you.
The real layout, with sample data. Nothing you click is sent or saved.
Good morning. 4 things need you. Most urgent: a stuck agent is still costing money.
- An agent has made no progress for 2 hA tool call is still pending. Stop it or start it again.$3.10 / h
- PR #214 broke a rule: force push to mainBlocked before it ran. The agent carried on.1 rule
- Search subagents run on the largest model418 of 483 this week. A smaller model is enough for search.−$38 / week
- This session has run for 9 hHand off to a fresh session to stop paying for old context.−$6 / day
All caught up.
-
Tokens2.4MSessions2ModelOpusRuleforce push to main · blocked
-
Tokens910kSessions1ModelSonnetRulesall kept
-
Tokens7.1MSessions7ModelOpusRulesall kept
-
Tokens380kSessions1ModelHaikuRulesall kept
Click a pull request to open its receipt.
- checkout-retryOpusstuck 2 h$3.10 / h
- invoice-exportSonnetrunning$1.20 / h
- search-docsOpusrunning$2.40 / h
- test-fixerHaikurunning$0.18 / h
- 8 moremixeddone$0.00 / h
- No force push to mainblocked PR #2141 hit
- No secrets in commits0 hits
- Ask before deleting files3 hits
- Stop an agent idle for 30 m2 hits
3 of 4 rules on.
Last 7 days · $126 · busiest Thursday, $31
- Opus54 %$71.40
- Sonnet31 %$18.90
- Haiku11 %$1.30
- Local 8B4 %$0.00
A smaller model is enough for 418 search calls on Opus this week. Move them to Haiku: −$38 / week
Questions
Does Earlyman change my setup on its own?
Only small changes marked safe, and each one is listed with its verdict date. Any change can be rolled back in one step.
How do I know a saving is real?
Each fix is compared against its baseline over the same kind of work, and shows saved as zero until its verdict lands.
What kind of fixes does it suggest?
Things like avoiding repeated reads, using a smaller model for small tasks, and stopping retries on a broken tool.