Add a new review agent that evaluates CLI source code, plans, or specs
for AI agent readiness using a severity-based rubric (Blocker/Friction/
Optimization). The agent includes framework-specific idiom knowledge for
Click, argparse, Cobra, clap, Commander/yargs/oclif, and Thor.
The companion principles guide synthesizes Anthropic, CLIG, and
CLI-Anything guidance into 7 practical principles with per-principle
evaluation tests and a recommended assessment flow.
Trevin Chow