[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1946":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},1946,"oh-my-claudecode","Yeachan-Heo\u002Foh-my-claudecode","Yeachan-Heo","Teams-first Multi-agent orchestration for Claude Code","https:\u002F\u002Foh-my-claudecode.dev",null,"TypeScript",36213,3294,127,1,0,83,441,2759,373,120,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36],"agentic-coding","ai-agents","automation","claude","claude-code","multi-agent-systems","oh-my-opencode","opencode","parallel-execution","vibe-coding","2026-06-12 04:00:12","English | [한국어](README.ko.md) | [中文](README.zh.md) | [日本語](README.ja.md) | [Español](README.es.md) | [Tiếng Việt](README.vi.md) | [Português](README.pt.md)\n\n# oh-my-claudecode\n\n[![npm version](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Foh-my-claude-sisyphus?color=cb3837)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Foh-my-claude-sisyphus)\n[![npm downloads](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002Foh-my-claude-sisyphus?color=blue)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Foh-my-claude-sisyphus)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYeachan-Heo\u002Foh-my-claudecode?style=flat&color=yellow)](https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-claudecode\u002Fstargazers)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![Sponsor](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSponsor-❤️-red?style=flat&logo=github)](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FYeachan-Heo)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1452487457085063218?color=5865F2&logo=discord&logoColor=white&label=Discord)](https:\u002F\u002Fdiscord.gg\u002FPUwSMR9XNk)\n\n> **For Codex users:** Check out [oh-my-codex](https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-codex) — the same orchestration experience for OpenAI Codex CLI.\n\n**Multi-agent orchestration for Claude Code. Zero learning curve.**\n\n_Don't learn Claude Code. Just use OMC._\n\n[Get Started](#quick-start) • [Documentation](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website) • [CLI Reference](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#cli-reference) • [Workflows](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#workflows) • [Migration Guide](docs\u002FMIGRATION.md) • [Discord](https:\u002F\u002Fdiscord.gg\u002FPUwSMR9XNk)\n\n---\n\n## Core Maintainers\n\n| Role | Name | GitHub |\n| --- | --- | --- |\n| Creator & Lead | Yeachan Heo | [@Yeachan-Heo](https:\u002F\u002Fgithub.com\u002FYeachan-Heo) |\n\n## Ambassadors\n\n| Name | GitHub |\n| --- | --- |\n| Sigrid Jin | [@sigridjineth](https:\u002F\u002Fgithub.com\u002Fsigridjineth) |\n\n## Document Specialists\n\n| Name | GitHub |\n| --- | --- |\n| devswha | [@devswha](https:\u002F\u002Fgithub.com\u002Fdevswha) |\n\n## Top Collaborators\n\n| Name | GitHub | Commits |\n| --- | --- | --- |\n| JunghwanNA | [@shaun0927](https:\u002F\u002Fgithub.com\u002Fshaun0927) | 65 |\n| riftzen-bit | [@riftzen-bit](https:\u002F\u002Fgithub.com\u002Friftzen-bit) | 52 |\n| Seunggwan Song | [@Nathan-Song](https:\u002F\u002Fgithub.com\u002FNathan-Song) | 20 |\n| BLUE | [@blue-int](https:\u002F\u002Fgithub.com\u002Fblue-int) | 20 |\n| Junho Yeo | [@junhoyeo](https:\u002F\u002Fgithub.com\u002Fjunhoyeo) | 15 |\n\n## Quick Start\n\n**Step 1: Install**\n\nMarketplace\u002Fplugin install (recommended for most Claude Code users).\nThese are Claude Code slash commands — enter them **one at a time** (pasting both lines at once will fail):\n\n```bash\n\u002Fplugin marketplace add https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-claudecode\n```\n\nThen:\n\n```bash\n\u002Fplugin install oh-my-claudecode\n```\n\nIf you prefer the npm CLI\u002Fruntime path instead of the marketplace flow:\n\n```bash\nnpm i -g oh-my-claude-sisyphus@latest\n```\n\n> **Known npm warning:** npm may print `deprecated prebuild-install@7.1.3` during the CLI install.\n> This currently comes from the upstream `better-sqlite3` native-addon dependency\n> (`better-sqlite3 -> prebuild-install`); `prebuild-install@7.1.3` is still the latest\n> published version, so there is no safe repo-side dependency bump or override to remove\n> the warning yet. The warning is tracked in [#2913](https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-claudecode\u002Fissues\u002F2913)\n> and does not by itself mean the OMC CLI install failed.\n\n**Step 2: Setup**\n\n```bash\n# Inside a Claude Code \u002F OMC session\n\u002Fsetup\n\u002Fomc-setup\n\n# From your terminal\nomc setup\n```\n\nIf you run OMC via `omc --plugin-dir \u003Cpath>` or `claude --plugin-dir \u003Cpath>`, add `--plugin-dir-mode` to `omc setup` (or export `OMC_PLUGIN_ROOT` before running it) so the installer doesn't duplicate skills\u002Fagents that the plugin already provides at runtime. See the [Plugin directory flags section in REFERENCE.md](.\u002Fdocs\u002FREFERENCE.md#plugin-directory-flags) for a complete decision matrix and all available flags.\n\n**Step 3: Build something**\n\n```bash\n# Inside a Claude Code \u002F OMC session\n\u002Fautopilot \"build a REST API for managing tasks\"\n\n# Natural-language in-session shortcut\nautopilot: build a REST API for managing tasks\n```\n\nThat's it. Everything else is automatic.\n\n### CLI Commands vs In-Session Skills\n\nOMC exposes two different surfaces:\n\n- **Terminal CLI commands**: run `omc ...` from your shell after installing the npm\u002Fruntime path (`npm i -g oh-my-claude-sisyphus@latest`) or from a local checkout.\n- **In-session skills**: run `\u002F...` inside a Claude Code session after installing the plugin\u002Fsetup flow.\n\n| Feature | Terminal CLI | In-session skill | Notes |\n| --- | --- | --- | --- |\n| Setup | `omc setup` | `\u002Fsetup` or `\u002Fomc-setup` | Both are real entrypoints. `\u002Fsetup` is the easiest plugin-first path. |\n| Ask providers | `omc ask codex \"review this patch\"` | `\u002Fask codex \"review this patch\"` | Both route through the same advisor flow. |\n| Team orchestration | `omc team 2:codex \"review auth flow\"` | `\u002Fteam 3:executor \"fix all TypeScript errors\"` | Both exist, but they are different runtimes: `omc team` launches tmux CLI workers; `\u002Fteam` runs the in-session native team workflow. |\n| Autopilot \u002F Ralph \u002F Ultrawork \u002F Deep Interview | — | `\u002Fautopilot ...`, `\u002Fralph ...`, `\u002Fultrawork ...`, `\u002Fdeep-interview ...` | These are in-session skills. There is no `omc autopilot` \u002F `omc ralph` \u002F `omc ultrawork` CLI subcommand in this repo. |\n| Autoresearch | `omc autoresearch` (**hard-deprecated shim**) | `\u002Fdeep-interview --autoresearch ...` + `\u002Foh-my-claudecode:autoresearch` | Setup stays in deep-interview; execution now belongs to the stateful skill. |\n\n### Not Sure Where to Start?\n\nIf you're uncertain about requirements, have a vague idea, or want to micromanage the design:\n\n```\n\u002Fdeep-interview \"I want to build a task management app\"\n```\n\nThe deep interview uses Socratic questioning to clarify your thinking before any code is written. It exposes hidden assumptions and measures clarity across weighted dimensions, ensuring you know exactly what to build before execution begins.\n\n## Team Mode (Recommended)\n\nStarting in **v4.1.7**, **Team** is the canonical orchestration surface in OMC. The legacy `swarm` keyword\u002Fskill has been removed; use `team` directly.\n\n```bash\n\u002Fteam 3:executor \"fix all TypeScript errors\"\n```\n\nUse `\u002Fteam ...` when you want Claude Code's in-session native team workflow. Use `omc team ...` when you want terminal-launched tmux CLI workers (`claude` \u002F `codex` \u002F `gemini` panes).\n\nTeam runs as a staged pipeline:\n\n`team-plan → team-prd → team-exec → team-verify → team-fix (loop)`\n\nEnable Claude Code native teams in `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"env\": {\n    \"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS\": \"1\"\n  }\n}\n```\n\n> If teams are disabled, OMC will warn you and fall back to non-team execution where possible.\n\n### tmux CLI Workers — Codex & Gemini (v4.4.0+)\n\n**v4.4.0 removes the Codex\u002FGemini MCP servers** (`x`, `g` providers). Use the CLI-first Team runtime (`omc team ...`) to spawn real tmux worker panes:\n\n```bash\nomc team 2:codex \"review auth module for security issues\"\nomc team 2:gemini \"redesign UI components for accessibility\"\nomc team 1:claude \"implement the payment flow\"\nomc team status auth-review\nomc team shutdown auth-review\n```\n\n`\u002Fomc-teams` remains as a legacy compatibility skill and now routes to `omc team ...`.\n\nFor mixed Codex + Gemini work in one command, use the **`\u002Fccg`** skill (routes via `\u002Fask codex` + `\u002Fask gemini`, then Claude synthesizes):\n\n```bash\n\u002Fccg Review this PR — architecture (Codex) and UI components (Gemini)\n```\n\n| Surface                   | Workers            | Best For                                     |\n| ------------------------- | ------------------ | -------------------------------------------- |\n| `omc team N:codex \"...\"`  | N Codex CLI panes  | Code review, security analysis, architecture |\n| `omc team N:gemini \"...\"` | N Gemini CLI panes | UI\u002FUX design, docs, large-context tasks      |\n| `omc team N:claude \"...\"` | N Claude CLI panes | General tasks via Claude CLI in tmux         |\n| `\u002Fccg`                    | \u002Fask codex + \u002Fask gemini | Tri-model advisor synthesis           |\n\nWorkers spawn on-demand and die when their task completes — no idle resource usage. Requires `codex` \u002F `gemini` CLIs installed and an active tmux session.\n\nNative team worker worktrees are being added behind an opt-in\u002Fconfig gate. See [Native Team Worktree Mode](docs\u002FTEAM-WORKTREE-MODE.md) for the workspace contract, canonical state-root rules, dirty-worktree preservation policy, and verification checklist.\n\n> **Note: Package naming** — The project is branded as **oh-my-claudecode** (repo, plugin, commands), but the npm package is published as [`oh-my-claude-sisyphus`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Foh-my-claude-sisyphus). If you install or upgrade the CLI tools via npm\u002Fbun, use `npm i -g oh-my-claude-sisyphus@latest`.\n\n### Updating\n\nIf you installed OMC via npm, upgrade with the published package name:\n\n```bash\nnpm i -g oh-my-claude-sisyphus@latest\n```\n\n> **Package naming note:** the repo, plugin, and commands are branded **oh-my-claudecode**, but the published npm package name remains `oh-my-claude-sisyphus`.\n\nIf you installed OMC via the Claude Code marketplace\u002Fplugin flow, update with:\n\n```bash\n# 1. Update the marketplace clone\n\u002Fplugin marketplace update omc\n\n# 2. Re-run setup to refresh configuration\n\u002Fsetup\n```\n\nIf you are developing from a local checkout or git worktree, update the checkout first, then re-run setup from that worktree so the active runtime matches the code you are testing.\n\n> **Note:** If marketplace auto-update is not enabled, you must manually run `\u002Fplugin marketplace update omc` to sync the latest version before running setup.\n\nIf you experience issues after updating, clear the old plugin cache:\n\n```bash\n\u002Fomc-doctor\n```\n\n\u003Ch1 align=\"center\">Your Claude Just Have been Steroided.\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fomc-character.jpg\" alt=\"oh-my-claudecode\" width=\"400\" \u002F>\n\u003C\u002Fp>\n\n---\n\n## Why oh-my-claudecode?\n\n- **Zero configuration required** - Works out of the box with intelligent defaults\n- **Team-first orchestration** - Team is the canonical multi-agent surface\n- **Natural language interface** - No commands to memorize, just describe what you want\n- **Automatic parallelization** - Complex tasks distributed across specialized agents\n- **Persistent execution** - Won't give up until the job is verified complete\n- **Cost optimization** - Smart model routing saves 30-50% on tokens\n- **Learn from experience** - Automatically extracts and reuses problem-solving patterns\n- **Real-time visibility** - HUD statusline shows what's happening under the hood\n\n---\n\n## Features\n\n### Orchestration Modes\n\nMultiple strategies for different use cases — from Team-backed orchestration to token-efficient refactoring. [Learn more →](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#execution-modes)\n\n| Mode                    | What it is                                                                              | Use For                                                |\n| ----------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------ |\n| **Team (recommended)**  | Canonical staged pipeline (`team-plan → team-prd → team-exec → team-verify → team-fix`) | Coordinated Claude agents on a shared task list        |\n| **omc team (CLI)**      | tmux CLI workers — real `claude`\u002F`codex`\u002F`gemini` processes in split-panes              | Codex\u002FGemini CLI tasks; on-demand spawn, die when done |\n| **ccg**                 | Tri-model advisors via `\u002Fask codex` + `\u002Fask gemini`, Claude synthesizes                   | Mixed backend+UI work needing both Codex and Gemini    |\n| **Autopilot**           | Autonomous execution (single lead agent)                                                | End-to-end feature work with minimal ceremony          |\n| **Ultrawork**           | Maximum parallelism (non-team)                                                          | Burst parallel fixes\u002Frefactors where Team isn't needed |\n| **Ralph**               | Persistent mode with verify\u002Ffix loops                                                   | Tasks that must complete fully (no silent partials)    |\n| **Pipeline**            | Sequential, staged processing                                                           | Multi-step transformations with strict ordering        |\n| **Ultrapilot (legacy)** | Deprecated compatibility mode (autopilot pipeline alias)                                | Existing workflows and older docs                      |\n\n### Intelligent Orchestration\n\n- **19 specialized agents** (with tier variants) for architecture, research, design, testing, data science\n- **Smart model routing** - Haiku for simple tasks, Opus for complex reasoning\n- **Automatic delegation** - Right agent for the job, every time\n\n### Developer Experience\n\n- **Magic keywords** - `ralph`, `ulw`, `ralplan`; Team stays explicit via `\u002Fteam`\n- **HUD statusline** - Real-time orchestration metrics in your status bar\n  - If you launch Claude Code directly with `claude --plugin-dir \u003Cpath>` (bypassing the `omc` shim), export `OMC_PLUGIN_ROOT=\u003Cpath>` in your shell so the HUD bundle resolves to the same checkout as the plugin loader. See the [Plugin directory flags section in REFERENCE.md](.\u002Fdocs\u002FREFERENCE.md#plugin-directory-flags) for details.\n- **Skill learning** - Extract reusable patterns from your sessions\n- **Analytics & cost tracking** - Understand token usage across all sessions\n\n### Contributing\n\nWant to contribute to OMC? See [CONTRIBUTING.md](.\u002FCONTRIBUTING.md) for the full developer guide, including how to fork, set up a local checkout, link it as your active plugin, run tests, and submit PRs.\n\n### Custom Skills\n\nLearn once, reuse forever. OMC extracts hard-won debugging knowledge into portable skill files that auto-inject when relevant.\n\n| | Project Scope | User Scope |\n|---|---|---|\n| **Path** | `.omc\u002Fskills\u002F` | `~\u002F.omc\u002Fskills\u002F` |\n| **Shared with** | Team (commit the skill file to keep it across worktrees) | All your projects |\n| **Priority** | Higher (overrides user) | Lower (fallback) |\n\n```yaml\n# .omc\u002Fskills\u002Ffix-proxy-crash.md\n---\nname: Fix Proxy Crash\ndescription: aiohttp proxy crashes on ClientDisconnectedError\ntriggers: [\"proxy\", \"aiohttp\", \"disconnected\"]\nsource: extracted\n---\nWrap handler at server.py:42 in try\u002Fexcept ClientDisconnectedError...\n```\n\n**Manage skills:** `\u002Fskill list | add | remove | edit | search`\n**Skillify:** `\u002Fskillify` extracts reusable patterns with strict quality gates\n**Auto-inject:** Matching skills load into context automatically — no manual recall needed\n\nProject-scoped skills are stored in `.omc\u002Fskills\u002F` and are intended to be committed when you want them shared. If you create them inside a linked git worktree and do not commit them, they disappear when that worktree is removed.\n\n[Full feature list →](docs\u002FREFERENCE.md)\n\n---\n\n## In-session shortcuts\n\nThese shortcuts run **inside a Claude Code \u002F OMC session**, not as terminal CLI commands. For shell commands, use the `omc ...` forms shown above. Team mode is explicit: use `\u002Fteam ...` in-session or `omc team ...` from your shell rather than expecting a bare `team` keyword trigger.\n\n| In-session form        | Kind                  | Effect                              | Example                                        |\n| ---------------------- | --------------------- | ----------------------------------- | ---------------------------------------------- |\n| `\u002Fteam`                | Slash skill           | Canonical Team orchestration        | `\u002Fteam 3:executor \"fix all TypeScript errors\"` |\n| `\u002Fccg`                 | Slash skill           | `\u002Fask codex` + `\u002Fask gemini` synthesis | `\u002Fccg review this PR`                       |\n| `\u002Fautopilot` \u002F `autopilot` | Skill \u002F prompt trigger | Full autonomous execution       | `\u002Fautopilot \"build a todo app\"`                |\n| `\u002Fralph` \u002F `ralph`     | Skill \u002F prompt trigger | Persistence mode                   | `\u002Fralph \"refactor auth\"`                       |\n| `\u002Fultrawork` \u002F `ulw`   | Skill \u002F prompt trigger | Maximum parallelism                | `\u002Fultrawork \"fix all errors\"`                  |\n| `\u002Fralplan` \u002F `ralplan` | Skill \u002F prompt trigger | Iterative planning consensus       | `\u002Fralplan \"plan this feature\"`                 |\n| `\u002Fdeep-interview`      | Slash skill           | Socratic requirements clarification | `\u002Fdeep-interview \"vague idea\"`                 |\n| `deepsearch`           | Prompt trigger        | Codebase-focused search routing     | `deepsearch for auth middleware`               |\n| `ultrathink`           | Prompt trigger        | Deep reasoning mode                 | `ultrathink about this architecture`           |\n| `cancelomc`, `stopomc` | Prompt trigger        | Stop active OMC modes               | `stopomc`                                      |\n\n**Notes:**\n\n- **ralph includes ultrawork**: when you activate ralph mode, it automatically includes ultrawork's parallel execution.\n- `swarm` compatibility alias has been removed; migrate existing prompts to `\u002Fteam` syntax.\n- `plan this` \u002F `plan the` keyword triggers were removed; use `ralplan` or explicit `\u002Foh-my-claudecode:omc-plan`.\n\n## Utilities\n\n### Provider Advisor (`omc ask` \u002F `\u002Fask`)\n\nRun local provider CLIs and save a markdown artifact under `.omc\u002Fartifacts\u002Fask\u002F`.\n\n```bash\n# Terminal CLI\nomc ask claude \"review this migration plan\"\nomc ask codex --prompt \"identify architecture risks\"\nomc ask gemini --prompt \"propose UI polish ideas\"\nomc ask claude --agent-prompt executor --prompt \"draft implementation steps\"\n\n# Inside a Claude Code \u002F OMC session\n\u002Fask claude \"review this migration plan\"\n\u002Fask codex \"identify architecture risks\"\n```\n\nCanonical env vars:\n\n- `OMC_ASK_ADVISOR_SCRIPT`\n- `OMC_ASK_ORIGINAL_TASK`\n\nPhase-1 aliases `OMX_ASK_ADVISOR_SCRIPT` and `OMX_ASK_ORIGINAL_TASK` are accepted with deprecation warnings.\n\n### Autoresearch (stateful skill)\n\n`omc autoresearch` is now a **hard-deprecated shim**. The authoritative workflow is:\n\n```bash\n\u002Fdeep-interview --autoresearch improve startup performance\n\u002Foh-my-claudecode:autoresearch\n```\n\n- `deep-interview --autoresearch` generates\u002Fsets up the mission and evaluator\n- `autoresearch` runs the bounded, single-mission stateful loop\n- each iteration records evaluation JSON plus markdown decision logs\n- non-passing iterations continue\n- strict stopping is controlled by an explicit max-runtime ceiling\n\n### Rate Limit Wait\n\nAuto-resume Claude Code sessions when rate limits reset.\n\n```bash\nomc wait          # Check status, get guidance\nomc wait --start  # Enable auto-resume daemon\nomc wait --stop   # Disable daemon\n```\n\n**Requires:** tmux (for session detection)\n\n### Monitoring & Observability\n\nUse the HUD for live observability and the current session\u002Freplay artifacts for post-session inspection:\n\n- HUD preset: `\u002Foh-my-claudecode:hud setup` then use a supported preset such as `\"omcHud\": { \"preset\": \"focused\" }`\n- Session summaries: `.omc\u002Fsessions\u002F*.json`\n- Replay logs: `.omc\u002Fstate\u002Fagent-replay-*.jsonl`\n- Live HUD rendering: `omc hud`\n\n### Notification Tags (Telegram\u002FDiscord\u002FSlack)\n\nYou can configure who gets tagged when stop callbacks send session summaries.\n\n```bash\n# Set\u002Freplace tag list\nomc config-stop-callback telegram --enable --token \u003Cbot_token> --chat \u003Cchat_id> --tag-list \"@alice,bob\"\nomc config-stop-callback discord --enable --webhook \u003Curl> --tag-list \"@here,123456789012345678,role:987654321098765432\"\nomc config-stop-callback slack --enable --webhook \u003Curl> --tag-list \"\u003C!here>,\u003C@U1234567890>\"\n\n# Incremental updates\nomc config-stop-callback telegram --add-tag charlie\nomc config-stop-callback discord --remove-tag @here\nomc config-stop-callback discord --clear-tags\n```\n\nTag behavior:\n\n- Telegram: `alice` becomes `@alice`\n- Discord: supports `@here`, `@everyone`, numeric user IDs, and `role:\u003Cid>`\n- Slack: supports `\u003C@MEMBER_ID>`, `\u003C!channel>`, `\u003C!here>`, `\u003C!everyone>`, `\u003C!subteam^GROUP_ID>`\n- `file` callbacks ignore tag options\n\n### OpenClaw Integration\n\nForward Claude Code session events to an [OpenClaw](https:\u002F\u002Fopenclaw.ai\u002F) gateway to enable automated responses and workflows via your OpenClaw agent.\n\n**Quick setup (recommended):**\n\n```bash\n\u002Foh-my-claudecode:configure-notifications\n# → When prompted, type \"openclaw\" → choose \"OpenClaw Gateway\"\n```\n\n**Manual setup:** create `~\u002F.claude\u002Fomc_config.openclaw.json`:\n\n```json\n{\n  \"enabled\": true,\n  \"gateways\": {\n    \"my-gateway\": {\n      \"url\": \"https:\u002F\u002Fyour-gateway.example.com\u002Fwake\",\n      \"headers\": { \"Authorization\": \"Bearer YOUR_TOKEN\" },\n      \"method\": \"POST\",\n      \"timeout\": 10000\n    }\n  },\n  \"hooks\": {\n    \"session-start\": { \"gateway\": \"my-gateway\", \"instruction\": \"Session started for {{projectName}}\", \"enabled\": true },\n    \"stop\":          { \"gateway\": \"my-gateway\", \"instruction\": \"Session stopping for {{projectName}}\", \"enabled\": true }\n  }\n}\n```\n\n**Environment variables:**\n\n| Variable | Description |\n|----------|-------------|\n| `OMC_OPENCLAW=1` | Enable OpenClaw |\n| `OMC_OPENCLAW_DEBUG=1` | Enable debug logging |\n| `OMC_OPENCLAW_CONFIG=\u002Fpath\u002Fto\u002Fconfig.json` | Override config file path |\n\n**Supported hook events (6 active in bridge.ts):**\n\n| Event | Trigger | Key template variables |\n|-------|---------|----------------------|\n| `session-start` | Session begins | `{{sessionId}}`, `{{projectName}}`, `{{projectPath}}` |\n| `stop` | Claude response completes | `{{sessionId}}`, `{{projectName}}` |\n| `keyword-detector` | Every prompt submission | `{{prompt}}`, `{{sessionId}}` |\n| `ask-user-question` | Claude requests user input | `{{question}}`, `{{sessionId}}` |\n| `pre-tool-use` | Before tool invocation (high frequency) | `{{toolName}}`, `{{sessionId}}` |\n| `post-tool-use` | After tool invocation (high frequency) | `{{toolName}}`, `{{sessionId}}` |\n\n**Reply channel environment variables:**\n\n| Variable | Description |\n|----------|-------------|\n| `OPENCLAW_REPLY_CHANNEL` | Reply channel (e.g. `discord`) |\n| `OPENCLAW_REPLY_TARGET` | Channel ID |\n| `OPENCLAW_REPLY_THREAD` | Thread ID |\n\nSee `scripts\u002Fopenclaw-gateway-demo.mjs` for a reference gateway that relays OpenClaw payloads to Discord via ClawdBot.\n\n---\n\n## Documentation\n\n- **[Full Reference](docs\u002FREFERENCE.md)** - Complete feature documentation\n- **[CLI Reference](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#cli-reference)** - All `omc` commands, flags, and tools\n- **[Notifications Guide](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#notifications)** - Discord, Telegram, Slack, and webhook setup\n- **[Recommended Workflows](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#workflows)** - Battle-tested skill chains for common tasks\n- **[Release Notes](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website\u002Fdocs\u002F#release-notes)** - What's new in each version\n- **[Website](https:\u002F\u002Fyeachan-heo.github.io\u002Foh-my-claudecode-website)** - Interactive guides and examples\n- **[Migration Guide](docs\u002FMIGRATION.md)** - Upgrade from v2.x\n- **[Architecture](docs\u002FARCHITECTURE.md)** - How it works under the hood\n- **[Performance Monitoring](docs\u002FPERFORMANCE-MONITORING.md)** - Agent tracking, debugging, and optimization\n- **[Security Guide](SECURITY.md)** - Enterprise deployment and hardening\n\n---\n\n## Requirements\n\n- [Claude Code](https:\u002F\u002Fdocs.anthropic.com\u002Fclaude-code) CLI\n- Claude Max\u002FPro subscription OR Anthropic API key\n\n### Platform & tmux\n\nOMC features like `omc team` and rate-limit detection require **tmux**:\n\n| Platform       | tmux provider                                            | Install                |\n| -------------- | -------------------------------------------------------- | ---------------------- |\n| macOS          | [tmux](https:\u002F\u002Fgithub.com\u002Ftmux\u002Ftmux)                    | `brew install tmux`    |\n| Ubuntu\u002FDebian  | tmux                                                     | `sudo apt install tmux`|\n| Fedora         | tmux                                                     | `sudo dnf install tmux`|\n| Arch           | tmux                                                     | `sudo pacman -S tmux`  |\n| Windows        | [psmux](https:\u002F\u002Fgithub.com\u002Fmarlocarlo\u002Fpsmux) (native)   | `winget install psmux` |\n| Windows (WSL2) | tmux (inside WSL)                                        | `sudo apt install tmux`|\n\n> **Windows users:** [psmux](https:\u002F\u002Fgithub.com\u002Fmarlocarlo\u002Fpsmux) provides a native `tmux` binary for Windows with 76 tmux-compatible commands. No WSL required.\n\n### Optional: Multi-AI Orchestration\n\nOMC can optionally orchestrate external AI providers for cross-validation and design consistency. These are **not required** — OMC works fully without them.\n\n| Provider                                                  | Install                             | What it enables                                  |\n| --------------------------------------------------------- | ----------------------------------- | ------------------------------------------------ |\n| [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) | `npm install -g @google\u002Fgemini-cli` | Design review, UI consistency (1M token context) |\n| [Codex CLI](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex)              | `npm install -g @openai\u002Fcodex`      | Architecture validation, code review cross-check |\n\n**Cost:** 3 Pro plans (Claude + Gemini + ChatGPT) cover everything for ~$60\u002Fmonth.\n\n---\n\n## License\n\nMIT\n\n---\n\n\u003Cdiv align=\"center\">\n\n**Inspired by:** [oh-my-opencode](https:\u002F\u002Fgithub.com\u002Fcode-yeongyu\u002Foh-my-opencode) • [claude-hud](https:\u002F\u002Fgithub.com\u002Fryanjoachim\u002Fclaude-hud) • [Superpowers](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers) • [everything-claude-code](https:\u002F\u002Fgithub.com\u002Faffaan-m\u002Feverything-claude-code) • [Ouroboros](https:\u002F\u002Fgithub.com\u002FQ00\u002Fouroboros)\n\n**Zero learning curve. Maximum power.**\n\n\u003C\u002Fdiv>\n\n\u003C!-- OMC:FEATURED-CONTRIBUTORS:START -->\n## Featured by OmC Contributors\n\nTop personal non-fork, non-archived repos from all-time OMC contributors (100+ GitHub stars).\n\n- [@Yeachan-Heo](https:\u002F\u002Fgithub.com\u002FYeachan-Heo) — [oh-my-claudecode](https:\u002F\u002Fgithub.com\u002FYeachan-Heo\u002Foh-my-claudecode) (⭐ 32k)\n- [@junhoyeo](https:\u002F\u002Fgithub.com\u002Fjunhoyeo) — [tokscale](https:\u002F\u002Fgithub.com\u002Fjunhoyeo\u002Ftokscale) (⭐ 2.3k)\n- [@psmux](https:\u002F\u002Fgithub.com\u002Fpsmux) — [psmux](https:\u002F\u002Fgithub.com\u002Fpsmux\u002Fpsmux) (⭐ 1.6k)\n- [@BowTiedSwan](https:\u002F\u002Fgithub.com\u002FBowTiedSwan) — [buildflow](https:\u002F\u002Fgithub.com\u002FBowTiedSwan\u002Fbuildflow) (⭐ 291)\n- [@alohays](https:\u002F\u002Fgithub.com\u002Falohays) — [awesome-visual-representation-learning-with-transformers](https:\u002F\u002Fgithub.com\u002Falohays\u002Fawesome-visual-representation-learning-with-transformers) (⭐ 268)\n- [@jcwleo](https:\u002F\u002Fgithub.com\u002Fjcwleo) — [random-network-distillation-pytorch](https:\u002F\u002Fgithub.com\u002Fjcwleo\u002Frandom-network-distillation-pytorch) (⭐ 261)\n- [@emgeee](https:\u002F\u002Fgithub.com\u002Femgeee) — [mean-tutorial](https:\u002F\u002Fgithub.com\u002Femgeee\u002Fmean-tutorial) (⭐ 200)\n- [@shaun0927](https:\u002F\u002Fgithub.com\u002Fshaun0927) — [openchrome](https:\u002F\u002Fgithub.com\u002Fshaun0927\u002Fopenchrome) (⭐ 186)\n- [@MeroZemory](https:\u002F\u002Fgithub.com\u002FMeroZemory) — [ida-multi-mcp](https:\u002F\u002Fgithub.com\u002FMeroZemory\u002Fida-multi-mcp) (⭐ 182)\n- [@anduinnn](https:\u002F\u002Fgithub.com\u002Fanduinnn) — [HiFiNi-Auto-CheckIn](https:\u002F\u002Fgithub.com\u002Fanduinnn\u002FHiFiNi-Auto-CheckIn) (⭐ 171)\n- [@HaD0Yun](https:\u002F\u002Fgithub.com\u002FHaD0Yun) — [Gopeak-godot-mcp](https:\u002F\u002Fgithub.com\u002FHaD0Yun\u002FGopeak-godot-mcp) (⭐ 148)\n- [@Znuff](https:\u002F\u002Fgithub.com\u002FZnuff) — [consolas-powerline](https:\u002F\u002Fgithub.com\u002FZnuff\u002Fconsolas-powerline) (⭐ 146)\n\n\u003C!-- OMC:FEATURED-CONTRIBUTORS:END -->\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=Yeachan-Heo\u002Foh-my-claudecode&type=date&legend=top-left)](https:\u002F\u002Fwww.star-history.com\u002F#Yeachan-Heo\u002Foh-my-claudecode&type=date&legend=top-left)\n\n## 💖 Support This Project\n\nIf Oh-My-ClaudeCode helps your workflow, consider sponsoring:\n\n[![Sponsor on GitHub](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSponsor-❤️-red?style=for-the-badge&logo=github)](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FYeachan-Heo)\n\n### Why sponsor?\n\n- Keep development active\n- Priority support for sponsors\n- Influence roadmap & features\n- Help maintain free & open source\n\n### Other ways to help\n\n- ⭐ Star the repo\n- 🐛 Report bugs\n- 💡 Suggest features\n- 📝 Contribute code\n","oh-my-claudecode 是一个面向团队的多智能体编排工具，专为 Claude Code 设计。它通过零学习曲线的方式简化了多智能体系统的管理和操作，使得用户无需深入了解 Claude Code 即可高效使用。项目采用 TypeScript 编写，支持并行执行、自动化工作流和多智能体系统协调等核心功能。适用于需要提高开发效率、实现复杂任务自动化的场景，特别是在多人协作的开发环境中。其简洁直观的命令行界面与强大的插件生态系统相结合，进一步提升了用户体验。",2,"2026-06-11 02:46:59","top_all"]