unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
Leonxlnx/unlazy
View on GitHub ↗Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
unlazy grew +12.4% in the last 30 days, ranks 83rd of 1,061 in Prompting & Scaffolding, last commit 52 days ago.
Star trajectory
70 days tracked+12.4% in 30d, above the Prompting & Scaffolding median of +1.4%.
Last commit 52 days ago, staler than the median of 28d.
How it compares in Prompting & Scaffolding
Ranked 83rd of 1,061 by stars.
- Language
- JavaScript
- License
- MIT License
- Contributors
- 12
- Forks
- 320
- Watchers
- 13
- Open issues
- 1
- Releases
- 0
- Created
- 2026-08-09
- Stars this week
- +136
You've seen where unlazy stands today.
Get the moves before everyone else: the 5 Prompting & Scaffolding repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.