Skill Claude CodeCodex
Use after meaningful instruction changes; replay behavior, test controls, and independently verify improvement.
not rated 9 2mo ago A 21 tokens
original MIT
Minimal, self-checking, simulation-driven improvement for AI agents
This repository also configures its own agents. See what smarter-agent tells them →
Skill Claude CodeCodex
Use after meaningful instruction changes; replay behavior, test controls, and independently verify improvement.