Judge Rubric

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.

Builds and maintains a persistent, interlinked Obsidian knowledge base by incrementally ingesting sources, updating entity/concept pages, and keeping cross-references current.

Makes AI responses feel more human by adding an inner dialogue loop that reflects on and revises the initial instinctive reply.

Logs board meeting decisions with a two-layer memory architecture, separating raw transcripts from approved decisions, and provides commands to review past decisions and overdue action items.

Compacts the current conversation into a handoff document for another agent to pick up, referencing existing artifacts by path or URL instead of duplicating them.