← All skills

Skill

Agent guardrails

Controls around AI tool use and agent actions. The supporting projects describe their limits.

Projects

  • excubitor — Safety Fences for Autonomous Coding Agents

    Project

    Excubitor carries coding work and feedback through fresh model contexts, repeating agreed checks and separate review until the checks and review pass, or a limit or blocker stops the run. The recording below follows its development controller through a repair.

Courses & credentials