Skill invocation runner: install an Agent Skill in a fresh fixture, invoke an agent harness headlessly, and report what actually reached the model, with transcript evidence.
Decide-then-code. A Claude Code plugin that teaches every load-bearing decision, records your choice, and blocks code from moving past a decision you have not made yet.
AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI