Judgment Layer

Add a judgment classifier to any agent or Claude Code skill to decide when to act autonomously vs. ask for confirmation. Evaluates each candidate action against three axes -- reversibility, bounded cost, and user observability -- and routes to act-now, ask-first, or queue-for-review. Outputs a PreToolUse hook configuration and a policy file. Use when asking "when should my agent ask?", "judgment layer", "add a confirmation gate", "my agent acts when it shouldn't", "reversibility check", or designing authority boundaries for an agent.

m2ai-portfolio Updated 4 repo stars

File contents

m2ai-portfolio/m2ai-skills-pack commit 8d69e70ad4

Frequently asked questions

npx get-skill add m2ai-portfolio/judgment-layer