@yeachan-heo

ai-slop-cleaner removes bloat from working code via deletion-first, regression-locked cleanup. it enforces scope boundaries, optional reviewer-only mode, and smell-focused passes without behavior drift.

skill manages oh-my-claudecode skills via cli commands, supporting list, add, remove, search, edit, sync and setup operations across built-in, user, and project scopes with yaml frontmatter metadata.

learner defines meta-standards for extracting reusable, non-generic skills from conversations and codebases. it emphasizes deep investigation, project-specificity, and actionable heuristics over copy-paste solutions.

ultraqa automates iterative qa cycles by running verification, diagnosing failures through an architect subagent, applying fixes, and repeating up to 5 times until the goal passes or a pattern emerges.

spawns n coordinated claude agents on a shared task list with stage-gated pipeline (plan, prd, exec, verify, fix). uses native team management, inter-agent messaging, task dependencies, and handoff documents. replaces legacy swarm.

external-context spawns parallel document-specialist agents to decompose queries into search facets, fetch external references, and synthesize findings with citations. useful for research-heavy tasks but lacks failure handling.

deepinit generates hierarchical AGENTS.md files across codebases to document directory structure, purpose, and ai-agent working guidelines. uses phased delegation and parent-reference navigation.

ralplan is an alias for consensus-driven iterative planning that routes requests through planner, architect, and critic agents with optional interactive checkpoints and elevated rigor for high-risk work.

project-session-manager automates isolated dev environments using git worktrees and optional tmux orchestration for parallel issue, pr, and feature work across repositories.

hud configures and manages statusline display presets for the OMC environment with commands to switch layouts (minimal, focused, full) and view current configuration state.

autopilot handles end-to-end autonomous execution from idea through working code, with trigger detection for hands-off requests and explicit guardrails against misuse in exploratory contexts.

ultrawork spawns concurrent task execution for independent workloads, positioning itself as a lightweight parallel dispatcher without completion guarantees or persistence.

Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode

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

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

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

Socratic deep interview with mathematical ambiguity gating before explicit execution approval

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

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

Configure popular MCP servers for enhanced agent capabilities

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

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

Diagnose and fix oh-my-claudecode installation issues

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