Health

Runs a tiered audit of your Claude Code setup when instructions stop working, MCP tools fail, or AI-generated code becomes hard to maintain. Checks agent config layers (AGENTS.md, config.toml, runtime files), verifier commands, hooks, and maintainability signals like hotspot ownership and wrapper patterns. Summary mode is cheap and fast. Deep mode spawns three inspector subagents for context, control, and code rot analysis, which burns tokens but catches instruction drift and missing verification surfaces. Flags findings by severity with copy-paste fixes. Good for debugging why Claude ignores your rules or when you suspect your setup has drifted. The multilingual trigger keywords and budget escalation logic show this was built by someone tired of configs quietly rotting.