28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.