The Depth Tree method decomposes work N layers deep, verifying each leaf unit against its own gates before integration. It installs via SKILL.md in Claude Code, Codex, and Cursor; a Stop hook that mechanically blocks turn-ending while gates are unmet is Claude Code only.

Topics

Task Decomposition Claude Code AI Agents Model Laziness Acceptance Gates

View on GitHub All Bookmarks

Discover Similar Content

William's Bookmark Library

/**/

GitHub - Leonxlnx/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.

github.comSaved August 16, 202610 min

Leonxlnx · via GitHub

Summary

unlazy is a skill for AI coding agents that enforces file-based acceptance gates with runnable Node.js checks to block premature task completion.

Topics

Task Decomposition Claude Code AI Agents Model Laziness Acceptance Gates

View on GitHub All Bookmarks