mcpField
P
principle-never-block-on-the-human

principle-never-block-on-the-human

github.com/michael-denyerAgent workflows3.6k874 installsUpdated today
Repository

About principle-never-block-on-the-human

An agent skill for asynchronous human supervision: proceed with reversible work, explain decisions afterward, and reserve confirmation for irreversible actions. It is intended for agents that should keep execution moving without taking product direction away from people.

Key features

  1. 01Proceed with reversible work
  2. 02Present results after acting
  3. 03Repair issues in later rounds
  4. 04Confirm irreversible actions
  5. 05Keep product direction with humans

Use cases

  1. 01Editing code without waiting for approval
  2. 02Handling reversible task changes
  3. 03Seeking confirmation before destructive actions

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/michael-denyer/pstack-claude --skill principle-never-block-on-the-human

After installing, type/principle-never-block-on-the-humanin Claude Code to confirm it loaded.

Details

From the project README

Never Block on the Human

The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.

  • Proceed, then present. Do the work, show the result. Don't ask "should I do X?" Do X, explain why.
  • Make the system self-healing. When you notice a problem, log it and fix it in the next round.
  • Irreversible actions (force-push, delete production data, send external messages) still require confirmation.
  • Reversible actions (write code, edit notes, split tasks) should proceed without blocking.
  • Product direction comes from the human. Execution should not block.

Comments

Markdown supported