Yeachan-Heo

Extract a learned skill from the current conversation

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

Deep codebase initialization with hierarchical AGENTS.md documentation

Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Configure popular MCP servers for enhanced agent capabilities

Self-referential loop until task completion with configurable verification reviewer

Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs

Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode

Autonomous evolutionary code improvement engine with tournament selection

Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow

Manage local skills - list, add, remove, search, edit, setup wizard

Turn a repeatable workflow from the current session into a reusable OMC skill draft

N coordinated agents on shared task list using Claude Code native teams

Parallel execution engine for high-throughput task completion

LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Full autonomous execution from idea to working code