Harness Engineering playbook — deterministic smoke/test/lint harness commands, strict architecture boundaries, entropy-control checks for autonomous agent workflows.

skills.sh skill for control-loop metalayer setup in agentic repos

Unifying control-systems metalayer for LLM-as-controller agent development. Typed schemas, safety shields, EGRI loops, consciousness stack.

Provide tools and best practices for building and running long-running AI coding agent harnesses with Claude Code integration.