Yeachan-Heo/oh-my-claudecode

AI Slop Cleaner removes code bloat, duplication, dead code, and needless abstraction from AI-generated code using a deletion-first, regression-safe workflow. It supports a reviewer-only mode to separate cleanup writing from review.

Ask routes a prompt through the local Claude, Codex, Gemini, Antigravity, Grok, or Cursor CLI via `omc ask` and persists the result as an ask artifact. Use it when you want to ask a local AI model a question or task and save the response.

Autopilot turns a brief product idea into working code by autonomously handling requirements analysis, technical design, planning, parallel implementation, QA cycling, and multi-perspective validation. Use it when you want hands-off execution from a 2-3 line description to verified, working software.

Autoresearch runs one mission through bounded, evaluator-driven iterations and records each decision in durable logs. Use it when you have an existing mission and want persistent improvement until an explicit stop condition or max runtime is reached.

CCG routes tasks through Codex and Antigravity/Gemini CLIs, then Claude synthesizes both outputs into one answer. Use it to get parallel external perspectives on architecture, code review, and UI without tmux team workers.

Cancel OMC Mode detects and cancels the active Oh My Claude Code mode such as autopilot, ralph, ultrawork, or swarm. Use it to cleanly exit a workflow, release tasks, and clear state files.

Commands exposes the /oh-my-claudecode:skill compatibility command so a Claude Code session can load the full OMC skill instructions on demand without loading the entire skill description in every session.

Configure Notifications sets up Telegram, Discord, or Slack notification integrations for Claude Code sessions so users are alerted when sessions end, need input, or complete background tasks.

Debug diagnoses current OMC or Claude Code session problems by inspecting logs, traces, state, and focused reproduction. Use it when a workflow breaks or runtime behavior is confusing and you need the root cause and smallest next fix.

Deep Dive runs a two-stage pipeline: trace investigates root causes in parallel, then deep-interview crystallizes requirements, with trace findings injected to avoid re-exploration. Use when a problem is ambiguous and needs investigation before requirements.

Deep Init creates comprehensive, hierarchical AGENTS.md documentation across a codebase to help AI agents understand directory purpose, relationships, and conventions.

Deep Interview turns vague ideas into spec-ready requirements through one-question-at-a-time Socratic interviewing and weighted ambiguity scoring. Use it when a user wants thorough clarification and no assumptions before execution.

External Context decomposes a query into parallel search facets and invokes document-specialist agents to fetch external documentation, references, and context with citations. Use it when you need up-to-date information from official docs, blogs, or the web for a technical question.

HUD configures the OMC (oh-my-claudecode) heads-up display for the Claude Code statusline, letting you switch between minimal, focused, and full presets. Use it to set up or repair the HUD, control displayed elements, and view agent status.

Learner extracts a learned skill from the current conversation, capturing hard-won debugging insights and non-obvious project-specific knowledge as reusable skill files with triggers and guidance.

Local Build Reminder prompts the user to run npm run build after editing TypeScript files when running OMC from a local fork. It triggers automatically whenever the AI notices changed src/**/*.ts files or local mode is active.

MCP Setup configures Model Context Protocol servers to extend Claude Code with tools like web search, filesystem access, and GitHub integration. Use it when agents need external capabilities.

Merge Readiness generates a human-readable explanation of a completed change and quizzes the human to verify they can explain why it exists, what changed, tradeoffs, risks, and team understanding before requesting merge approval.

OMC Doctor diagnoses and fixes oh-my-claudecode installation issues by running diagnostics across plugin version, legacy hooks, CLAUDE.md markers, Ruby dependency, and stale cache.

OMC Reference provides the OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry for Claude Code sessions. Use it when delegating to agents, orchestrating teams, making commits, or invoking OMC skills.

OMC Setup installs, refreshes, or repairs oh-my-claudecode for plugin, npm, and local-dev setups. Use it after installing via plugin marketplace or npm, or when updating a local development checkout.

OMC Teams launches N CLI agent workers in tmux panes to execute tasks in parallel across claude, codex, gemini, antigravity, grok, or cursor. Use it when you need process-based parallel execution of independent subtasks.

Plan creates comprehensive, actionable work plans by interviewing the user for vague requests or generating directly from detailed requests, with optional consensus and review modes.

Project Session Manager automates isolated development environments using git worktrees and tmux sessions for reviewing PRs, fixing issues, and building features. It supports GitHub and Jira project references, aliases, and attach/kill/status session commands.

Ralph keeps working on a task until every user story in prd.json passes and is reviewer-verified. It wraps parallel execution with session persistence, automatic retry, and mandatory verification before completion.