AI product Open source
unlazy is an agent skill for enforcing completion discipline in substantial AI-agent tasks. It requires an acceptance ledger to be written first, with runnable CHECK commands and EXPECT conditions; its gate checker reviews commands, executes approved gates, records evidence, and can reverify completed work. The skill also supports a Depth Tree method that splits tasks into fresh-context subtasks with integration checks, giving each leaf the full task time budget. It can be installed for supported agents with the skills CLI or manually for Claude Code and Codex CLI; its checker and optional hook require Node.js 16 or newer and no third-party runtime packages.
2 uses taken from transcripts — each links to the moment in the video.
An agent skill that turns task completion into a checked evidence ledger. It creates acceptance gates with runnable commands, records evidence, and can split larger jobs into fresh-context subtasks with integration checks.
An agent skill that turns requirements into an acceptance ledger containing runnable commands and expected output. It lets agents split work into scoped leaves, claim non-overlapping paths, and reverify results before reporting completion.
2 in the library.