Hudy

Research existing tools, libraries, and patterns before writing custom code by invoking a researcher agent.

Periodically scans Claude Code configuration for redundant, stale, or orphaned items and walks the user through a confirm-each-deletion cleanup.

Reduces token usage by ~75% by stripping filler words, articles, and pleasantries while preserving full technical accuracy. Activates on user commands like 'caveman mode' or 'be brief'.

Interviews users relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

Honestly evaluate AI work quality using a two-axis scoring system with mandatory devil's advocate reasoning and cross-session anti-inflation detection.

Create, edit, and verify agent skills using test-driven development to ensure agents follow documented procedures correctly.