vision
25Agent
Visual analysis specialist — screenshots, mockups, UI comparisons, error screenshots, and design implementation guidance.
Agent
Visual analysis specialist — screenshots, mockups, UI comparisons, error screenshots, and design implementation guidance.
Command
Autonomous execution mode — break a goal into tasks and execute them sequentially with safety checkpoints.
Command
Deep analysis with opus model. Use for complex debugging, architectural decisions, difficult bugs, security analysis, and tasks requiring careful reasoning.
Command
Deep project initialization — generate hierarchical AGENTS.md, CLAUDE.md, and directory-level documentation.
Command
Multi-perspective parallel code review — analyze git diff from 5 viewpoints simultaneously.
Command
Diagnose plugin health — check dependencies, hooks, agents, and runtime state.
Command
Generate a session handoff document capturing current work state, progress, and context for the next session or developer.
Command
View session history — past sessions, duration, tool usage, and trends.
Command
Auto-generate CLAUDE.md by analyzing project structure, dependencies, conventions, and patterns. Creates a comprehensive project instruction file.
Command
Ralph Loop — persistent iterative execution with automatic verification, failure adaptation, and completion detection. Keeps running until the task passes all checks or max iterations are reached.
Command
Mode management — show active mode, mode history, and manage mode state.
Command
Configure notification channels for session completion alerts (Discord, Slack, Telegram).
Command
Multi-stage quality pipeline — Plan, Implement, Verify, Fix, Review with automated gate checks.
Command
Generate PR metadata — title, description, changed files summary, and test plan.
Command
Auto QA loop — run tests, analyze failures, fix, and retest automatically.
Command
Fast execution with haiku model. Use for simple questions, quick lookups, small edits, and tasks where speed matters more than depth.
Command
Iterative consensus planning — structured plan-critique-revise cycles until agreement.
Command
Release management — version bumping, changelog generation, and release notes.
Command
Code review based on git diff. Reviews staged/unstaged changes or a specific commit range for bugs, security issues, and code quality.
Command
Decompose a complex task into parallel subtasks and generate tmux commands for concurrent execution with separate worktrees.
Command
Display session metrics dashboard — tool calls, context usage, active modes, and notification status.
Command
Swarm mode — dispatch multiple parallel agents for research, analysis, or bulk operations.
Command
Create an Agent Teams setup with N workers + reviewer for parallel task execution with worktree isolation and merge coordination.
Command
Ultrawork — activate ALL available specialized agents in maximum parallel execution for comprehensive task coverage.