unlazy: open-source skill fights AI agent laziness with runnable gates

tom_doerr · x · 2026-09-05

unlazy (3k stars on GitHub) is an anti-laziness skill for AI agents. Its core Depth Tree method splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. It enforces completion discipline: write an acceptance ledger first, run executable gates, re-verify returned work, and only report what evidence supports. Grounded in 2025-2026 research on model laziness and underthinking; installable via npx skills add Leonxlnx/unlazy.

Original post →

More from coding & agent

coding & agent channel →