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.
More from coding & agent
- The Story of VS Code documentary debuts, noting Antigravity, Cursor, Windsurf are all forks — 0xkarasy · 2026-09-05
- TRACES agent benchmark grades live execution loops, not answers — SucceededMind · 2026-09-05
- Dev says GPT-6 Astra found 4.5x to 176x speedups in his codebase in 5 minutes — charliermarsh · 2026-09-05
- Update Codex CLI for remote connections to access Astra — benjamin_warner · 2026-09-05
- OpenAI Announces GPT-6 Astra Hackathons in SF and NYC, $50K Credits Top Prize — OpenAIDevs · 2026-09-05
- Astra implements entire design system in Figma, taking over designers' grunt work — AIandDesign · 2026-09-05