Runnable Loop Engineering for Claude Code — scheduled, stateful AI agent loops with an earned L1→L3 autonomy ladder, maker/checker verification, a pre-run cost gate, and pluggable engines (Claude, local Ollama, OpenCode, or any CLI).
Skill Claude CodeCodex
Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.
Skill Claude CodeCodex
The checker half of a maker/checker loop. Independently reviews a proposed fix before it becomes a PR. Has authority to REJECT. Never makes changes itself.