stet-cli

Contextual Stet documentation for agents; not the operating contract.

Use Stet to measure whether an AI coding change is safe to ship. Trigger on model comparisons, AGENTS.md or CLAUDE.md effectiveness, shared instruction, policy, skill, harness, tool-policy, reasoning, or runtime rollouts, repo eval setup, dataset building, regression detection, benchmarking, promote/rollback decisions, and questions like "is this helping", "compare models on my repo", "test this change", "what regressed", "keep improving until it passes", "which model should I use", or "should this become the default".