omg

Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality

Route questions to Claude, Codex, or Gemini for multi-perspective answers

Claude-Codex-Gemini tri-model orchestration — decompose, query, synthesize

Health check — verifies omg plugin is correctly installed and working

Quick reference — what omg agents and skills are available and how to use them

About omg — version, architecture, capabilities, and credits

Agent directory — lists all omg agents with their roles, models, and when to use each

Clean AI-generated code — remove unnecessary abstractions, verbose comments, over-engineering

Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean

Cancel any active execution mode — stops autopilot, ralph, ultrawork, team, ultraqa cleanly

Set up notification integrations — Telegram, Discord, Slack alerts for long-running tasks

Structured debugging — reproduce, diagnose, fix with @omg:debugger agent

Deep analysis mode — multi-agent investigation of complex systems or problems

Activates investigation-to-requirements pipeline — trace root cause then crystallize into actionable spec

Socratic deep interview with ambiguity scoring — crystallize vague ideas into clear specs before execution

Deep codebase initialization — generate comprehensive documentation for unfamiliar codebases

Deep codebase search — thorough multi-angle exploration with cross-validation

External documentation and web research via parallel document-specialist agents

Standard persistence and handoff protocol for inter-agent communication

Extract a reusable skill from the current conversation — learn from what just worked

Auto-detect and install Microsoft Copilot Skills — Fabric, Azure SQL, DevOps, Power Platform

omg entry point — routes requests to the right agent or skill. Say 'omg' followed by what you need.

Strategic planning — interview workflow, direct planning, consensus mode, or plan review

Manage development sessions — branch isolation for issues, PRs, and features

Activates strict completion mode — keeps working until ALL acceptance criteria pass with verified proof

Activates consensus planning — multi-perspective review with planner, architect, and critic

Automated release workflow — version bump, changelog, tag, validation

Save persistent notes and context that survive across sessions

Activates deep investigation → cloud agent PR creation (Copilot-exclusive)

Activates parallel research — staged scientist agents investigate from multiple angles

Activates autonomous code improvement — competing strategies, benchmarking, tournament selection

Cross-session persistent context — remember project decisions, architecture choices, and team conventions

Convert a successful workflow into a reusable SKILL.md file

Test-Driven Development mode — strict red-green-refactor discipline

Activates parallel team execution — N coordinated agents working simultaneously on independent subtasks

Evidence-driven tracing — orchestrate competing hypotheses to explain observed outcomes

Interactive guided tour of omg — progressive walkthrough from discovery to full orchestration

QA cycling — test, diagnose, fix, repeat until quality goal is met

Deep reasoning mode — engage opus-class model for complex analysis requiring extended thinking

Activates parallel execution — fires multiple agents simultaneously for independent tasks