Claude commands

Capture and retrieve PR review knowledge in project memory palaces.

Create and manage memory palaces, the unified storage for knowledge captured from research sessions.

Search and navigate across memory palaces to find and retrieve stored information.

Manage and analyze digital gardens for evolving knowledge bases, including health metrics.

Verify plugin behavioral contract history via GitHub Attestations (SLSA)

Update all installed Claude Code plugins from all marketplaces.

Uninstall and reinstall all Claude Code plugins to refresh cache and resolve version mismatches.

Start a structured review workflow with evidence logging and formatted output

Display stewardship health dimensions for one or all plugins

Pre-flight gate walking four Karpathy principles (think first, simplicity, surgical edits, goal-driven). Use before implementation.

Audit changes for additive bias, Iron Law compliance, and minimal intervention. Justifies every change against a "simplest safe change" standard.

Context recovery after session breaks. Summarize recent git changes, extract key decisions, and identify pending work.

List all rules with their status

Install a rule from the catalog

Create behavioral rules to prevent unwanted actions

Display help and documentation

Convert Python SDK hooks to declarative rules

Interactive interface to enable/disable rules

Run an ad-hoc gauntlet challenge session (5 questions, random scope)

Show challenge accuracy stats, weak areas, and streak

Start or resume a guided onboarding path

Build, search, and query the code knowledge graph

Rebuild the knowledge base from the current codebase

Add or edit a knowledge annotation