Self-hosted alternatives to principle-never-block-on-the-human

P

principle-never-block-on-the-human

Apply when tempted to ask 'should I do X?' on reversible work

principle-never-block-on-the-human is an agent skill from Cursor's plugins collection that applies a working principle to reversible work. The principle starts from the observation that the human supervises asynchronously, so an agent should stay unblocked: make reasonable decisions, proceed, and let the human correct course afterwards. Since code changes are reversible and reviewable, a wrong decision usually costs less than stopping to ask. The skill asks the agent to proceed, then present: do the work, show the result, and explain why, rather than asking whether it should do the work. When the agent notices a problem, it should log it and fix it in the next round, which makes the system self-healing. The principle draws a clear line. Irreversible actions, such as force-pushing, deleting production data or sending external messages, still require confirmation. Reversible actions, such as writing code, editing notes or splitting tasks, should proceed without blocking. Product direction still comes from the human, but execution should not stop for every choice. The principle is most useful in long autonomous runs where each question would otherwise halt the work. It is listed on skills.sh, where the page shows install counts and GitHub stars for the Cursor plugins repository. Install it with npx skills add https://github.com/cursor/plugins --skill principle-never-block-on-the-human.