unlazy
Unlazy is a skill for Claude Code and other AI coding agents that stops them from calling a task done before it actually is, by breaking work into a verifiable tree of gated sub-tasks.
View leonxlnx/unlazy on GitHub- GitHub stars
- 4,379
- Forks
- —
- Language
- JavaScript
Project details
- Repository
- leonxlnx/unlazy
- Licence
- MIT
- Primary language
- JavaScript
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
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.
Explore by topic
More tools in Skills & plugins
- ecc
affaan-m · MIT
An open-source performance layer for AI coding agents like Claude Code, Codex and Cursor, adding memory, skills and security so agents keep context and work more…
- ponytail
dietrichgebert · MIT
ponytail is a skill for AI coding agents that makes them behave like a lazy senior developer: write the least code needed, skip unnecessary abstraction, and stop the…
- caveman
juliusbrussee · Apache-2.0
Caveman is a free skill that makes Claude Code and other AI coding agents write shorter, more compact responses, cutting token usage and cost without losing substance.
- paperclip
paperclipai · MIT
An open-source dashboard where you hire a team of AI agents (Claude Code, Codex, Cursor, OpenClaw, etc.), give them a business goal, set budgets, and watch them work…