agentleFS
Sign inStart free
jaydubya818jaydubya818/MissionControl/skills/principle-never-block-on-the-human/SKILL.md

principle-never-block-on-the-human

Skill2 starsChanged 8 months agoMITView on GitHub

Apply when safe reversible implementation details can proceed inside scope.

We split this skill into the rules it gives an agent

4 rules. 2 are common, 2 are distinctive, and 0 are very specific to this project.

  • 2

    Common

    Most of the 30 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Why: Every permission pause stalls the pipeline and makes the human the bottleneck.

    line 20
  2. Distinctive:

    Reserve questions for genuine ambiguity: Ask only when you cannot infer intent from context.

    line 24
  3. Common:

    Make the system self-healing: When you notice a problem, log it and fix it in the next round.

    line 25
  4. Distinctive:

    In-scope implementation should not stall: Write code, edit local notes, and split internal tasks when those actions stay within the …

    line 32

“Common” is measured: kept by at least 6 in 10 of the 30 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Never Block on the Human

The human can supervise implementation asynchronously. Make reasonable low-risk decisions inside the authorized scope, then present the result for review.

Why: Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.

Pattern:

  • Proceed, then present. Handle reversible implementation details that do not change product intent, authority, cost, or external state. Show the result and explain why.
  • Reserve questions for genuine ambiguity. Ask only when you cannot infer intent from context.
  • Make the system self-healing. When you notice a problem, log it and fix it in the next round.
  • Supervision is async. Design workflows for review-after-the-fact.

Boundaries:

  • Approval policy wins. Mission Control contracts plus system, user, and repository instructions define what the agent may do.
  • External writes need authority. Messages, tickets, pull-request mutations, eval launches, publishing, merges, deploys, spending, and destructive cleanup do not become authorized merely because they are reversible.
  • Product direction stays with the human. Experiments can inform a decision; they do not make the decision.
  • In-scope implementation should not stall. Write code, edit local notes, and split internal tasks when those actions stay within the accepted outcome and scope.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free