An early, AI-assisted prototype for agents to discover and use static Markdown methods and templates has been shared for design feedback. The system decouples discovery from delivery by returning short search candidates rather than full documents.
- Search returns a few short candidates, not the full catalog or document bodies.
- Resolve checks declared usage rights, required capabilities, permissions and dependency costs against host policy.
- Acquire records access; read delivers a fixed version with timeout handling for unknown results.
- Feedback reuses an existing check or allows an unknown result without requiring another model call.
The author notes that passing format rules does not establish task quality and there is no evidence yet that this saves total tokens or improves real user outcomes. The intended commercial model involves seller-set prices with a 10% transaction commission, though payments are currently disabled.