yeachan-heo

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

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Configure HUD display options (layout, presets, display elements)

Deep codebase initialization with hierarchical AGENTS.md documentation

Full autonomous execution from idea to working code

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow

Self-referential loop until task completion with configurable verification reviewer

Structured visual QA verdict for screenshot-to-reference comparisons

QA cycling workflow - test, verify, fix, repeat until goal met

N coordinated agents on shared task list using Claude Code implicit agent teams

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state

Diagnose and fix oh-my-claudecode installation issues

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

Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Invoke parallel document-specialist agents for external web searches and documentation lookup

Configure notification integrations (Telegram, Discord, Slack) via natural language

Strategic planning with optional interview workflow

Autonomous evolutionary code improvement engine with tournament selection

Parallel execution engine for high-throughput task completion

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

Verify that a change really works before you claim completion

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

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

Configure popular MCP servers for enhanced agent capabilities

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

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

Agentic memory system for writers - track characters, relationships, scenes, and themes

Extract a learned skill from the current conversation

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

Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode

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

CLI-team runtime for claude, codex, gemini, antigravity, grok, or cursor workers in tmux panes when you need process-based parallel execution

Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session

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

Investigate an open question and return grounded, sourced findings

Evaluate finished work for defects, risk, and simplification before it ships

YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface appearing on first use, so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.

Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort whose destination is unclear is routed to /ask-navigator before this pipeline starts). Humans own the checkpoints where there is no unique answer or the error cost is severe; agents continuously run everything repeatable and acceptable-by-evidence.

Remind the user to rebuild OMC after editing TypeScript when running from a local fork. Triggered automatically by the AI whenever it notices it (or the user) just changed a src//.ts file in an OMC dev install.

Test-first at pre-agreed seams — one test, one implementation, tracer-bullet red/green; independent expected values; substitutions only at the seam's boundary class; launch Phase 4 reference.

Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.