oh-my-auggie

Query with a specific model — get a targeted answer from a named model

Full autonomous execution — expand requirements, plan, implement in parallel, QA, multi-perspective validation

Cancel active OMA mode and clear all state

Tri-model orchestration — synthesize opus + gemini + gpt-5.4 perspectives, finalize in sonnet

Socratic deep interview with mathematical ambiguity gating — thorough requirements gathering before execution

Generate hierarchical AGENTS.md — comprehensive multi-agent architecture document

Regression-safe anti-slop cleanup — identify and fix low-quality AI artifacts, verbose patterns, and over-engineered code

Diagnose OMA installation issues — check plugin health, dependencies, and configuration

Show all available OMA commands or detailed help for a specific command

Configure HUD display — customize heads-up display for real-time execution metrics

Socratic requirements gathering — ask probing questions to extract complete requirements

Extract learned skill from conversation — create reusable skill from demonstrated expertise

Configure MCP servers — add, remove, and manage Model Context Protocol server connections

Write to notepad — priority, working memory, or manual notes

Configure notifications — Telegram, Discord, and Slack alerts for OMA events

Strategic planning with analyst/architect review — structured approach for complex tasks

Persistence loop — keeps working until task is complete and verified by architect

Autonomous hackathon lifecycle — PRD via deep-interview, ralph loop execution, auto-hardening

Consensus planning — Planner/Architect/Critic multi-agent loop until consensus is reached

Automated release workflow — versioning, changelog, tagging, and publication

Parallel research via document-specialist agents — gather comprehensive information quickly

Science/research workflow — hypothesis → experiment → analysis → conclusion

Search across all session history — find past decisions, code, and context quickly

Worktree-first dev environment manager — create, manage, and switch development worktrees

Install or refresh OMA — set up plugin, hooks, agents, and skills

Manage OMA skills — list, add, remove, search, and edit skills

List all available OMA skills and their descriptions

Show the current OMA mode, active task, and iteration count

Coordinated team of N agents working in parallel (requires external oma CLI companion)

Create git worktrees instantly — for issues, PRs, and features in isolation

Evidence-driven causal tracing — trace decision paths to understand outcomes

QA cycling — test, verify, fix, repeat until quality passes

High-throughput parallel subagent execution — spawn multiple agents simultaneously for maximum speed

Structured visual QA — compare screenshots, validate UI changes, and report regressions

Rate limit monitoring and auto-resume — wait for Claude API limits to clear

Agentic memory for writers — persistent context across writing sessions

Requirements clarity and hidden constraints. Use for "analyze requirements", "find edge cases", and "identify risks" before implementation.

System design, architecture analysis, and implementation verification. Use for "design X", "analyze architecture", "debug root cause", and "verify implementation".

Comprehensive code review. Use for "review this code", "assess quality", and "find issues" in implementation.

Plan/design challenge and review. Use for "critique this plan", "challenge this design", and "find weaknesses".

Root-cause analysis and failure diagnosis. Use for "debug this", "find the bug", and "diagnose failure".

UX and interaction design. Use for "design this feature", "UX review", and "interaction design".

SDK/API/docs lookup. Use for "find docs", "look up API", and "get documentation".

Implementation specialist. Writes, edits, and verifies code. Use for "implement X", "add Y", "refactor Z", and all code changes.

Fast codebase search, file mapping, and code pattern discovery. Use for "where is X?", "which files contain Y?", and "how does Z connect?" questions.

Commit strategy and history hygiene. Use for "git strategy", "commit message review", and "history cleanup".

Strategic planning with structured consultation. Creates clear, actionable 3-6 step plans with acceptance criteria.

Runtime/manual validation. Use for "QA this", "manual test", and "runtime validation".

Data analysis and statistical reasoning. Use for "analyze this data", "find patterns", and "statistical analysis".

Trust boundaries and vulnerabilities. Use for "security review", "find vulnerabilities", and "assess trust boundaries".

Behavior-preserving simplification. Use for "simplify this", "reduce complexity", and "clean up without changing behavior".

Testing strategy and regression coverage. Use for "add tests", "improve test coverage", and "design testing strategy".

Trace gathering and evidence capture. Use for "trace this", "gather evidence", and "capture execution flow".

Completion evidence and validation. Use for "verify this works", "check completion", and "gather evidence" after implementation.

Documentation and concise content. Use for "write docs", "update README", and "create content".

Route questions to appropriate intelligence. Use for "ask", "query", and "external knowledge".

Claude-Codex-Gemini tri-model orchestration. Use for "multi-model", "codex", "gemini", and "tri-model routing".

Root-cause analysis — isolate regressions, interpret stack traces, and resolve build/compilation errors

2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Deep project initialization with hierarchical AGENTS.md. Use for "initialize project", "create agents", "hierarchical setup".

Remove AI slop - low-quality, generic, or verbose content. Use for "clean up", "remove fluff", and "make concise".

Diagnose and fix common issues. Use for "debug", "fix this", "what's wrong", and "doctor".

Parallel document-specialist agents for external web searches and documentation lookup

HUD statusline and progress display. Use for "show status", "progress", "HUD", and "statusline".

Socratic interview and ambiguity scoring. Use for "interview", "question", "socratic", and "ambiguity".

Extract learned skills from conversations. Use for "learn this", "extract skill", and "capture knowledge".

Configure MCP servers and integrations. Use for "setup MCP", "configure server", and "MCP integration".

Create and manage notes during work. Use for "take note", "remember this", and "save for later".

Configure notification delivery. Use for "notify me", "setup notifications", "alert", and "notification config".

Strategic planning and task decomposition. Use for "plan this", "break down", and "roadmap".

Consensus planning - agree before executing. Use for "ralplan", "consensus", "pre-execution review".

Automated release workflow and versioning. Use for "release", "version", "publish", and "changelog".

Memory triage workflow — capture, organize, and retrieve persistent context

Research and investigation skills. Use for "research this", "investigate", "find out", and "deep dive".

Scientific analysis and data reasoning. Use for "analyze", "scientific method", "hypothesis", and "research".

Autonomous improvement loop — tournament selection with benchmark-driven iteration (HIGH COMPLEXITY — deferred)

Worktree and session management. Use for "new session", "worktree", "tmux", and "session management".

Setup routing and environment configuration. Use for "setup", "configure", and "get started".

Skill management and creation. Use for "create skill", "manage skills", "skill info", and "skill help".

N coordinated agents on shared task list using Claude Code native teams, with git worktree isolation per executor

Evidence-driven tracing and execution tracking. Use for "trace this", "execution trace", and "track progress".

QA cycling - test, verify, fix, repeat until quality. Use for "quality assurance", "test driven", and "verify thoroughly".

Parallel execution engine for concurrent agent tasks. Use for "run in parallel", "concurrent execution", and "ultrawork".

Evidence-driven verification discipline — verify claims before acting

Visual QA verdict for screenshots and UI. Use for "verify UI", "visual check", "screenshot verdict", and "visual comparison".

Agentic memory for writers. Use for "remember this", "write from memory", and "context preservation".

7 hooks across 4 events