claudecode-omc 4.4.10 → 4.7.4

package/README.ko.md

@@ -8,11 +8,13 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
 [![Sponsor](https://img.shields.io/badge/Sponsor-❤️-red?style=flat&logo=github)](https://github.com/sponsors/Yeachan-Heo)
 
+> **Codex 사용자분들께:** [oh-my-codex](https://github.com/Yeachan-Heo/oh-my-codex)를 확인해보세요 — OpenAI Codex CLI를 위한 동일한 오케스트레이션 경험을 제공합니다.
+
 **Claude Code를 위한 멀티 에이전트 오케스트레이션. 학습 곡선 제로.**
 
 *Claude Code를 배우지 마세요. 그냥 OMC를 쓰세요.*
 
-[시작하기](#빠른-시작) • [문서](https://yeachan-heo.github.io/oh-my-claudecode-website) • [마이그레이션 가이드](docs/MIGRATION.md)
+[시작하기](#빠른-시작) • [문서](https://yeachan-heo.github.io/oh-my-claudecode-website) • [CLI 레퍼런스](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference) • [워크플로우](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows) • [마이그레이션 가이드](docs/MIGRATION.md)
 
 ---
 
@@ -36,9 +38,19 @@ autopilot: build a REST API for managing tasks
 
 끝입니다. 나머지는 모두 자동입니다.
 
+### 어디서 시작해야 할지 모르겠다면?
+
+요구사항이 불확실하거나, 막연한 아이디어만 있거나, 설계를 세밀하게 관리하고 싶다면:
+
+```
+/deep-interview "I want to build a task management app"
+```
+
+딥 인터뷰는 소크라테스식 질문법을 사용하여 코드를 작성하기 전에 사고를 명확하게 합니다. 숨겨진 가정을 드러내고 가중치 기반 차원으로 명확성을 측정하여, 실행 시작 전에 무엇을 만들어야 하는지 정확히 알 수 있게 합니다.
+
 ## Team Mode (권장)
 
-**v4.1.7**부터 **Team**이 OMC의 표준 오케스트레이션 방식입니다. **swarm** 및 **ultrapilot** 같은 레거시 엔트리포인트는 계속 지원되지만, 이제 **내부적으로 Team으로 라우팅**됩니다.
+**v4.1.7**부터 **Team**이 OMC의 표준 오케스트레이션 방식입니다. 레거시 `swarm` 키워드/스킬은 제거되었으니 `team`을 직접 사용하세요.
 
 ```bash
 /team 3:executor "fix all TypeScript errors"
@@ -62,30 +74,34 @@ Team은 단계별 파이프라인으로 실행됩니다:
 
 ### tmux CLI 워커 — Codex & Gemini (v4.4.0+)
 
-**v4.4.0에서 Codex/Gemini MCP 서버**(`x`, `g` 프로바이더)가 **제거됩니다**. `/omc-teams`를 사용하여 tmux 분할 창에서 실제 CLI 프로세스를 실행하세요:
+**v4.4.0에서 Codex/Gemini MCP 서버**(`x`, `g` 프로바이더)가 **제거됩니다**. CLI 우선 Team 런타임(`omc team ...`)으로 tmux 분할 창에서 실제 CLI 프로세스를 실행하세요:
 
 ```bash
-/omc-teams 2:codex   "review auth module for security issues"
-/omc-teams 2:gemini  "redesign UI components for accessibility"
-/omc-teams 1:claude  "implement the payment flow"
+omc team 2:codex "review auth module for security issues"
+omc team 2:gemini "redesign UI components for accessibility"
+omc team 1:claude "implement the payment flow"
+omc team status auth-review
+omc team shutdown auth-review
 ```
 
+`/omc-teams`는 레거시 호환 스킬로 유지되며, 현재는 내부적으로 `omc team ...`으로 라우팅됩니다.
+
 하나의 명령으로 Codex + Gemini 작업을 처리하려면 **`/ccg`** 스킬을 사용하세요:
 
 ```bash
 /ccg Review this PR — architecture (Codex) and UI components (Gemini)
 ```
 
-| 스킬 | 워커 | 최적 용도 |
+| 실행 표면 | 워커 | 최적 용도 |
 |-------|---------|----------|
-| `/omc-teams N:codex` | N개 Codex CLI 창 | 코드 리뷰, 보안 분석, 아키텍처 |
-| `/omc-teams N:gemini` | N개 Gemini CLI 창 | UI/UX 디자인, 문서, 대용량 컨텍스트 |
-| `/omc-teams N:claude` | N개 Claude CLI 창 | tmux에서 Claude CLI를 통한 일반 작업 |
-| `/ccg` | Codex 1개 + Gemini 1개 | 병렬 트라이-모델 오케스트레이션 |
+| `omc team N:codex "..."` | N개 Codex CLI 창 | 코드 리뷰, 보안 분석, 아키텍처 |
+| `omc team N:gemini "..."` | N개 Gemini CLI 창 | UI/UX 디자인, 문서, 대용량 컨텍스트 |
+| `omc team N:claude "..."` | N개 Claude CLI 창 | tmux에서 Claude CLI를 통한 일반 작업 |
+| `/ccg` | ask-codex + ask-gemini | Codex+Gemini 조언을 Claude가 통합 |
 
 워커는 요청 시 생성되고 작업 완료 후 종료됩니다 — 유휴 리소스 낭비 없음. `codex` / `gemini` CLI가 설치되어 있고 활성 tmux 세션이 필요합니다.
 
-> **참고: 패키지 이름** — 프로젝트 브랜드명은 **oh-my-claudecode** (저장소, 플러그인, 명령어)이지만, npm 패키지는 [`claudecode-omc`](https://www.npmjs.com/package/claudecode-omc)로 배포됩니다. npm/bun으로 CLI 도구를 설치할 때는 `npm install -g claudecode-omc`를 사용하세요.
+> **참고: 패키지 이름** — 프로젝트 브랜드명은 **oh-my-claudecode** (저장소, 플러그인, 명령어)이며, npm 패키지는 [`claudecode-omc`](https://www.npmjs.com/package/claudecode-omc)로 배포됩니다. npm/bun으로 CLI 도구를 설치할 때는 `npm install -g claudecode-omc`를 사용하세요.
 
 ### 업데이트
 
@@ -117,6 +133,7 @@ omc doctor
 ## 왜 oh-my-claudecode인가?
 
 - **설정 불필요** - 똑똑한 기본값으로 바로 작동합니다
+- **Team 우선 오케스트레이션** - Team은 표준 멀티 에이전트 인터페이스입니다 (swarm/ultrapilot은 호환성 파사드)
 - **자연어 인터페이스** - 외울 명령어 없이, 원하는 것만 설명하세요
 - **자동 병렬화** - 복잡한 작업을 전문 에이전트들에게 분산합니다
 - **지속적 실행** - 작업이 완전히 검증될 때까지 포기하지 않습니다
@@ -134,7 +151,7 @@ omc doctor
 | 모드 | 특징 | 용도 |
 |------|---------|---------|
 | **Team (권장)** | 단계별 파이프라인 | 공유 작업 목록에서 협력하는 Claude 에이전트 |
-| **omc-teams** | tmux CLI 워커 | Codex/Gemini CLI 작업; 요청 시 실행, 완료 후 종료 |
+| **omc team (CLI)** | tmux CLI 워커 | Codex/Gemini CLI 작업; 요청 시 실행, 완료 후 종료 |
 | **ccg** | 트라이-모델 병렬 | Codex(분석) + Gemini(디자인), Claude가 통합 |
 | **Autopilot** | 자율 실행 | 최소한의 설정으로 end-to-end 기능 개발 |
 | **Ultrawork** | 최대 병렬 | Team이 필요 없는 병렬 수정/리팩토링 |
@@ -150,7 +167,7 @@ omc doctor
 
 ### 개발자 경험
 
-- **매직 키워드** - 명시적 제어를 위한 `ralph`, `ulw`, `plan`
+- **매직 키워드** - 명시적 제어를 위한 `ralph`, `ulw`, `team`
 - **HUD 상태바** - 상태바에서 실시간 오케스트레이션 메트릭 확인
 - **스킬 학습** - 세션에서 재사용 가능한 패턴 추출
 - **분석 및 비용 추적** - 모든 세션의 토큰 사용량 이해
@@ -166,17 +183,21 @@ omc doctor
 | 키워드 | 효과 | 예시 |
 |---------|--------|---------|
 | `team` | 표준 Team 오케스트레이션 | `/team 3:executor "fix all TypeScript errors"` |
-| `omc-teams` | tmux CLI 워커 (codex/gemini/claude) | `/omc-teams 2:codex "security review"` |
+| `omc team` | tmux CLI 워커 (codex/gemini/claude) | `omc team 2:codex "security review"` |
 | `ccg` | 트라이-모델 Codex+Gemini 오케스트레이션 | `/ccg review this PR` |
 | `autopilot` | 완전 자율 실행 | `autopilot: build a todo app` |
 | `ralph` | 지속 모드 | `ralph: refactor auth` |
 | `ulw` | 최대 병렬화 | `ulw fix all errors` |
 | `plan` | 계획 인터뷰 | `plan the API` |
 | `ralplan` | 반복적 계획 합의 | `ralplan this feature` |
-| `swarm` | 레거시 키워드 (Team으로 라우팅) | `swarm 5 agents: fix lint errors` |
-| `ultrapilot` | 레거시 키워드 (Team으로 라우팅) | `ultrapilot: build a fullstack app` |
+| `deep-interview` | 소크라테스식 요구사항 명확화 | `deep-interview "vague idea"` |
+| `swarm` | **지원 종료** — `team`을 사용하세요 | `swarm 5 agents: fix lint errors` |
+| `ultrapilot` | **지원 종료** — `team`을 사용하세요 | `ultrapilot: build a fullstack app` |
 
-**ralph는 ultrawork를 포함합니다:** ralph 모드를 활성화하면 자동으로 ultrawork의 병렬 실행이 포함됩니다. 키워드를 결합할 필요가 없습니다.
+**참고:**
+- **ralph는 ultrawork를 포함합니다:** ralph 모드를 활성화하면 자동으로 ultrawork의 병렬 실행이 포함됩니다. 키워드를 결합할 필요가 없습니다.
+- `/omc-teams`는 레거시 호환 경로로 남아 있으며 내부적으로 `omc team ...`으로 라우팅됩니다.
+- `swarm N agents` 구문은 에이전트 수 추출을 위해 여전히 인식되지만, v4.1.7+에서 런타임은 Team 기반입니다.
 
 ---
 
@@ -218,47 +239,17 @@ omc config-stop-callback discord --clear-tags
 
 ---
 
-## 알림 (Notifications)
-
-세션 라이프사이클 이벤트에 대해 실시간 알림을 받을 수 있습니다.
-
-지원 이벤트:
-- `session-start`
-- `session-stop` (persistent 모드가 대기/블록 상태로 들어갈 때)
-- `session-end`
-- `ask-user-question`
-
-### 설정
-쉘 프로필(예: `~/.zshrc`, `~/.bashrc`)에 환경 변수를 추가하세요:
-
-```bash
-# Discord Bot
-export OMC_DISCORD_NOTIFIER_BOT_TOKEN="your_bot_token"
-export OMC_DISCORD_NOTIFIER_CHANNEL="your_channel_id"
-
-# Telegram
-export OMC_TELEGRAM_BOT_TOKEN="your_bot_token"
-export OMC_TELEGRAM_CHAT_ID="your_chat_id"
-
-# Slack
-export OMC_SLACK_WEBHOOK_URL="your_webhook_url"
-export OMC_SLACK_MENTION="<@U1234567890>"  # optional
-
-# Optional webhooks
-export OMC_DISCORD_WEBHOOK_URL="your_webhook_url"
-```
-
-> 참고: `claude`를 실행하는 동일한 쉘에서 환경 변수가 로드되어 있어야 합니다.
-
----
-
 ## 문서
 
 - **[전체 레퍼런스](docs/REFERENCE.md)** - 완전한 기능 문서
-- **[성능 모니터링](docs/PERFORMANCE-MONITORING.md)** - 에이전트 추적, 디버깅 및 최적화
+- **[CLI 레퍼런스](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference)** - 모든 `omc` 명령어, 플래그 및 도구
+- **[알림 가이드](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#notifications)** - Discord, Telegram, Slack 및 webhook 설정
+- **[추천 워크플로우](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows)** - 일반 작업을 위한 검증된 스킬 체인
+- **[릴리스 노트](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#release-notes)** - 각 버전의 새로운 기능
 - **[웹사이트](https://yeachan-heo.github.io/oh-my-claudecode-website)** - 인터랙티브 가이드와 예제
 - **[마이그레이션 가이드](docs/MIGRATION.md)** - v2.x에서 업그레이드
 - **[아키텍처](docs/ARCHITECTURE.md)** - 내부 작동 원리
+- **[성능 모니터링](docs/PERFORMANCE-MONITORING.md)** - 에이전트 추적, 디버깅 및 최적화
 
 ---
 
@@ -288,7 +279,7 @@ MIT
 
 <div align="center">
 
-**영감을 받은 프로젝트:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/NexTechFusion/Superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code)
+**영감을 받은 프로젝트:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/obra/superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code) • [Ouroboros](https://github.com/Q00/ouroboros)
 
 **학습 곡선 제로. 최대 파워.**
 

package/README.md

@@ -12,7 +12,7 @@ Multi-agent orchestration for Claude Code with zero-friction setup.
 
 [Quick Start](#quick-start) • [Reference](docs/REFERENCE.md) • [Architecture](docs/ARCHITECTURE.md) • [Migration](docs/MIGRATION.md)
 
----
+_Don't learn Claude Code. Just use OMC._
 
 ## What Changed
 
@@ -26,22 +26,22 @@ This project is branded as **oh-my-claudecode**, and the npm package is publishe
 
 ## Quick Start
 
-### 1. Install
+**Step 1: Install**
 
 ```bash
 npm install -g claudecode-omc
 ```
 
-### 2. Bootstrap Claude Code Integration
+**Step 2: Setup**
 
 ```bash
 omc install
 omc setup
 ```
 
-### 3. Start Working
+**Step 3: Build something**
 
-```text
+```
 autopilot: build a REST API for managing tasks
 ```
 
@@ -79,9 +79,19 @@ omc doctor
 
 ---
 
+### Not Sure Where to Start?
+
+If you're uncertain about requirements, have a vague idea, or want to micromanage the design:
+
+```
+/deep-interview "I want to build a task management app"
+```
+
+The 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.
+
 ## Team Mode (Recommended)
 
-Team is the canonical orchestration surface.
+Starting in **v4.1.7**, **Team** is the canonical orchestration surface in OMC. The legacy `swarm` keyword/skill has been removed; use `team` directly.
 
 ```text
 team 3:executor "fix all TypeScript errors"
@@ -105,17 +115,155 @@ To enable Claude Code native teams, add this to `~/.claude/settings.json`:
 
 ## Core Features
 
-- Team-first orchestration
-- Autopilot, Ralph, Ultrawork, Pipeline execution modes
-- Specialized agent delegation with tiered model routing
-- Hook-driven automation and verification loops
-- Built-in analytics and cost tracking
+**v4.4.0 removes the Codex/Gemini MCP servers** (`x`, `g` providers). Use the CLI-first Team runtime (`omc team ...`) to spawn real tmux worker panes:
+
+```bash
+omc team 2:codex "review auth module for security issues"
+omc team 2:gemini "redesign UI components for accessibility"
+omc team 1:claude "implement the payment flow"
+omc team status auth-review
+omc team shutdown auth-review
+```
+
+`/omc-teams` remains as a legacy compatibility skill and now routes to `omc team ...`.
+
+For mixed Codex + Gemini work in one command, use the **`/ccg`** skill (routes via `ask-codex` + `ask-gemini`, then Claude synthesizes):
+
+```bash
+/ccg Review this PR — architecture (Codex) and UI components (Gemini)
+```
+
+| Surface                   | Workers            | Best For                                     |
+| ------------------------- | ------------------ | -------------------------------------------- |
+| `omc team N:codex "..."`  | N Codex CLI panes  | Code review, security analysis, architecture |
+| `omc team N:gemini "..."` | N Gemini CLI panes | UI/UX design, docs, large-context tasks      |
+| `omc team N:claude "..."` | N Claude CLI panes | General tasks via Claude CLI in tmux         |
+| `/ccg`                    | ask-codex + ask-gemini | Tri-model advisor synthesis             |
 
-See full details in [docs/REFERENCE.md](docs/REFERENCE.md).
+Workers spawn on-demand and die when their task completes — no idle resource usage. Requires `codex` / `gemini` CLIs installed and an active tmux session.
+
+> **Note: Package naming** — The project is branded as **oh-my-claudecode** (repo, plugin, commands), and the npm package is published as [`claudecode-omc`](https://www.npmjs.com/package/claudecode-omc). If you install the CLI tools via npm/bun, use `npm install -g claudecode-omc`.
+
+### Updating
+
+```bash
+# 1. Update the marketplace clone
+/plugin marketplace update omc
+
+# 2. Re-run setup to refresh configuration
+/omc-setup
+```
+
+> **Note:** If marketplace auto-update is not enabled, you must manually run `/plugin marketplace update omc` to sync the latest version before running setup.
+
+If you experience issues after updating, clear the old plugin cache:
+
+```bash
+/omc-doctor
+```
+
+<h1 align="center">Your Claude Just Have been Steroided.</h1>
+
+<p align="center">
+  <img src="assets/omc-character.jpg" alt="oh-my-claudecode" width="400" />
+</p>
+
+---
+
+## Why oh-my-claudecode?
+
+- **Zero configuration required** - Works out of the box with intelligent defaults
+- **Team-first orchestration** - Team is the canonical multi-agent surface
+- **Natural language interface** - No commands to memorize, just describe what you want
+- **Automatic parallelization** - Complex tasks distributed across specialized agents
+- **Persistent execution** - Won't give up until the job is verified complete
+- **Cost optimization** - Smart model routing saves 30-50% on tokens
+- **Learn from experience** - Automatically extracts and reuses problem-solving patterns
+- **Real-time visibility** - HUD statusline shows what's happening under the hood
 
 ---
 
-## Useful Commands
+## Features
+
+### Orchestration Modes
+
+Multiple strategies for different use cases — from Team-backed orchestration to token-efficient refactoring. [Learn more →](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#execution-modes)
+
+| Mode                    | What it is                                                                              | Use For                                                |
+| ----------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| **Team (recommended)**  | Canonical staged pipeline (`team-plan → team-prd → team-exec → team-verify → team-fix`) | Coordinated Claude agents on a shared task list        |
+| **omc team (CLI)**      | tmux CLI workers — real `claude`/`codex`/`gemini` processes in split-panes              | Codex/Gemini CLI tasks; on-demand spawn, die when done |
+| **ccg**                 | Tri-model advisors via ask-codex + ask-gemini, Claude synthesizes                         | Mixed backend+UI work needing both Codex and Gemini    |
+| **Autopilot**           | Autonomous execution (single lead agent)                                                | End-to-end feature work with minimal ceremony          |
+| **Ultrawork**           | Maximum parallelism (non-team)                                                          | Burst parallel fixes/refactors where Team isn't needed |
+| **Ralph**               | Persistent mode with verify/fix loops                                                   | Tasks that must complete fully (no silent partials)    |
+| **Pipeline**            | Sequential, staged processing                                                           | Multi-step transformations with strict ordering        |
+| **Ultrapilot (legacy)** | Deprecated compatibility mode (autopilot pipeline alias)                                | Existing workflows and older docs                      |
+
+### Intelligent Orchestration
+
+- **32 specialized agents** for architecture, research, design, testing, data science
+- **Smart model routing** - Haiku for simple tasks, Opus for complex reasoning
+- **Automatic delegation** - Right agent for the job, every time
+
+### Developer Experience
+
+- **Magic keywords** - `ralph`, `ulw`, `team` for explicit control
+- **HUD statusline** - Real-time orchestration metrics in your status bar
+- **Skill learning** - Extract reusable patterns from your sessions
+- **Analytics & cost tracking** - Understand token usage across all sessions
+
+[Full feature list →](docs/REFERENCE.md)
+
+---
+
+## Magic Keywords
+
+Optional shortcuts for power users. Natural language works fine without them.
+
+| Keyword                | Effect                                 | Example                                        |
+| ---------------------- | -------------------------------------- | ---------------------------------------------- |
+| `team`                 | Canonical Team orchestration           | `/team 3:executor "fix all TypeScript errors"` |
+| `omc team`             | tmux CLI workers (codex/gemini/claude) | `omc team 2:codex "security review"`           |
+| `ccg`                  | ask-codex + ask-gemini synthesis       | `/ccg review this PR`                          |
+| `autopilot`            | Full autonomous execution              | `autopilot: build a todo app`                  |
+| `ralph`                | Persistence mode                       | `ralph: refactor auth`                         |
+| `ulw`                  | Maximum parallelism                    | `ulw fix all errors`                           |
+| `ralplan`              | Iterative planning consensus           | `ralplan this feature`                         |
+| `deep-interview`       | Socratic requirements clarification    | `deep-interview "vague idea"`                  |
+| `deepsearch`           | Codebase-focused search routing        | `deepsearch for auth middleware`               |
+| `ultrathink`           | Deep reasoning mode                    | `ultrathink about this architecture`           |
+| `cancelomc`, `stopomc` | Stop active OMC modes                  | `stopomc`                                      |
+
+**Notes:**
+
+- **ralph includes ultrawork**: when you activate ralph mode, it automatically includes ultrawork's parallel execution.
+- `swarm` compatibility alias has been removed; migrate existing prompts to `/team` syntax.
+- `plan this` / `plan the` keyword triggers were removed; use `ralplan` or explicit `/oh-my-claudecode:omc-plan`.
+
+## Utilities
+
+### Provider Advisor (`omc ask`)
+
+Run local provider CLIs and save a markdown artifact under `.omc/artifacts/ask/`:
+
+```bash
+omc ask claude "review this migration plan"
+omc ask codex --prompt "identify architecture risks"
+omc ask gemini --prompt "propose UI polish ideas"
+omc ask claude --agent-prompt executor --prompt "draft implementation steps"
+```
+
+Canonical env vars:
+
+- `OMC_ASK_ADVISOR_SCRIPT`
+- `OMC_ASK_ORIGINAL_TASK`
+
+Phase-1 aliases `OMX_ASK_ADVISOR_SCRIPT` and `OMX_ASK_ORIGINAL_TASK` are accepted with deprecation warnings.
+
+### Rate Limit Wait
+
+Auto-resume Claude Code sessions when rate limits reset.
 
 ```bash
 omc --help
@@ -127,6 +275,54 @@ omc config-stop-callback --help
 omc hud
 ```
 
+**Requires:** tmux (for session detection)
+
+### Monitoring & Analytics
+
+Use the HUD for live observability and `omc` for cost/session reporting:
+
+- HUD analytics preset: `/oh-my-claudecode:hud setup` then set `"omcHud": { "preset": "analytics" }`
+- Cost reports: `omc cost daily|weekly|monthly`
+- Session history/backfill: `omc sessions`, `omc backfill`
+- Raw logs: `.omc/state/token-tracking.jsonl`, `.omc/state/agent-replay-*.jsonl`
+
+### Notification Tags (Telegram/Discord/Slack)
+
+You can configure who gets tagged when stop callbacks send session summaries.
+
+```bash
+# Set/replace tag list
+omc config-stop-callback telegram --enable --token <bot_token> --chat <chat_id> --tag-list "@alice,bob"
+omc config-stop-callback discord --enable --webhook <url> --tag-list "@here,123456789012345678,role:987654321098765432"
+omc config-stop-callback slack --enable --webhook <url> --tag-list "<!here>,<@U1234567890>"
+
+# Incremental updates
+omc config-stop-callback telegram --add-tag charlie
+omc config-stop-callback discord --remove-tag @here
+omc config-stop-callback discord --clear-tags
+```
+
+Tag behavior:
+
+- Telegram: `alice` becomes `@alice`
+- Discord: supports `@here`, `@everyone`, numeric user IDs, and `role:<id>`
+- Slack: supports `<@MEMBER_ID>`, `<!channel>`, `<!here>`, `<!everyone>`, `<!subteam^GROUP_ID>`
+- `file` callbacks ignore tag options
+
+---
+
+## Documentation
+
+- **[Full Reference](docs/REFERENCE.md)** - Complete feature documentation
+- **[CLI Reference](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference)** - All `omc` commands, flags, and tools
+- **[Notifications Guide](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#notifications)** - Discord, Telegram, Slack, and webhook setup
+- **[Recommended Workflows](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows)** - Battle-tested skill chains for common tasks
+- **[Release Notes](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#release-notes)** - What's new in each version
+- **[Website](https://yeachan-heo.github.io/oh-my-claudecode-website)** - Interactive guides and examples
+- **[Migration Guide](docs/MIGRATION.md)** - Upgrade from v2.x
+- **[Architecture](docs/ARCHITECTURE.md)** - How it works under the hood
+- **[Performance Monitoring](docs/PERFORMANCE-MONITORING.md)** - Agent tracking, debugging, and optimization
+
 ---
 
 ## Requirements
@@ -140,7 +336,10 @@ Optional multi-AI orchestration:
 - [Gemini CLI](https://github.com/google-gemini/gemini-cli)
 - [Codex CLI](https://github.com/openai/codex)
 
----
+| Provider                                                  | Install                             | What it enables                                  |
+| --------------------------------------------------------- | ----------------------------------- | ------------------------------------------------ |
+| [Gemini CLI](https://github.com/google-gemini/gemini-cli) | `npm install -g @google/gemini-cli` | Design review, UI consistency (1M token context) |
+| [Codex CLI](https://github.com/openai/codex)              | `npm install -g @openai/codex`      | Architecture validation, code review cross-check |
 
 ## Documentation
 
@@ -163,3 +362,37 @@ Optional multi-AI orchestration:
 ## License
 
 MIT
+
+---
+
+<div align="center">
+
+**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/obra/superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code) • [Ouroboros](https://github.com/Q00/ouroboros)
+
+**Zero learning curve. Maximum power.**
+
+</div>
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=Yeachan-Heo/oh-my-claudecode&type=date&legend=top-left)](https://www.star-history.com/#Yeachan-Heo/oh-my-claudecode&type=date&legend=top-left)
+
+## 💖 Support This Project
+
+If Oh-My-ClaudeCode helps your workflow, consider sponsoring:
+
+[![Sponsor on GitHub](https://img.shields.io/badge/Sponsor-❤️-red?style=for-the-badge&logo=github)](https://github.com/sponsors/Yeachan-Heo)
+
+### Why sponsor?
+
+- Keep development active
+- Priority support for sponsors
+- Influence roadmap & features
+- Help maintain free & open source
+
+### Other ways to help
+
+- ⭐ Star the repo
+- 🐛 Report bugs
+- 💡 Suggest features
+- 📝 Contribute code

package/README.pt.md

@@ -8,11 +8,13 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
 [![Sponsor](https://img.shields.io/badge/Sponsor-❤️-red?style=flat&logo=github)](https://github.com/sponsors/Yeachan-Heo)
 
+> **Para usuários do Codex:** Confira [oh-my-codex](https://github.com/Yeachan-Heo/oh-my-codex) — a mesma experiência de orquestração para o OpenAI Codex CLI.
+
 **Orquestração multiagente para Claude Code. Curva de aprendizado zero.**
 
 *Não aprenda Claude Code. Só use OMC.*
 
-[Começar Rápido](#início-rápido) • [Documentação](https://yeachan-heo.github.io/oh-my-claudecode-website) • [Guia de Migração](docs/MIGRATION.md)
+[Começar Rápido](#início-rápido) • [Documentação](https://yeachan-heo.github.io/oh-my-claudecode-website) • [Referência CLI](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference) • [Workflows](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows) • [Guia de Migração](docs/MIGRATION.md)
 
 ---
 
@@ -36,6 +38,16 @@ autopilot: build a REST API for managing tasks
 
 É isso. Todo o resto é automático.
 
+### Não sabe por onde começar?
+
+Se você não tem certeza sobre os requisitos, tem uma ideia vaga, ou quer microgerenciar o design:
+
+```
+/deep-interview "I want to build a task management app"
+```
+
+A entrevista profunda usa questionamento socrático para esclarecer seu pensamento antes de escrever qualquer código. Ela expõe suposições ocultas e mede a clareza por dimensões ponderadas, garantindo que você saiba exatamente o que construir antes da execução começar.
+
 ## Modo Team (Recomendado)
 
 A partir da **v4.1.7**, o **Team** é a superfície canônica de orquestração no OMC. Entrypoints legados como **swarm** e **ultrapilot** continuam com suporte, mas agora **roteiam para Team por baixo dos panos**.
@@ -85,7 +97,7 @@ Para trabalho misto de Codex + Gemini em um único comando, use a skill **`/ccg`
 
 Trabalhadores são iniciados sob demanda e encerrados quando a tarefa é concluída — sem uso ocioso de recursos. Requer as CLIs `codex` / `gemini` instaladas e uma sessão tmux ativa.
 
-> **Observação: Nome do pacote** — O projeto usa a marca **oh-my-claudecode** (repo, plugin, comandos), mas o pacote npm é publicado como [`claudecode-omc`](https://www.npmjs.com/package/claudecode-omc). Se você instalar as ferramentas de CLI via npm/bun, use `npm install -g claudecode-omc`.
+> **Observação: Nome do pacote** — O projeto usa a marca **oh-my-claudecode** (repo, plugin, comandos), e o pacote npm é publicado como [`claudecode-omc`](https://www.npmjs.com/package/claudecode-omc). Se você instalar as ferramentas de CLI via npm/bun, use `npm install -g claudecode-omc`.
 
 ### Atualizando
 
@@ -174,8 +186,9 @@ Atalhos opcionais para usuários avançados. Linguagem natural funciona bem sem
 | `ulw` | Paralelismo máximo | `ulw fix all errors` |
 | `plan` | Entrevista de planejamento | `plan the API` |
 | `ralplan` | Consenso de planejamento iterativo | `ralplan this feature` |
-| `swarm` | Palavra-chave legada (roteia para Team) | `swarm 5 agents: fix lint errors` |
-| `ultrapilot` | Palavra-chave legada (roteia para Team) | `ultrapilot: build a fullstack app` |
+| `deep-interview` | Esclarecimento socrático de requisitos | `deep-interview "vague idea"` |
+| `swarm` | **Descontinuado** — use `team` em vez disso | `swarm 5 agents: fix lint errors` |
+| `ultrapilot` | **Descontinuado** — use `team` em vez disso | `ultrapilot: build a fullstack app` |
 
 **Notas:**
 - **ralph inclui ultrawork**: quando você ativa o modo ralph, ele inclui automaticamente a execução paralela do ultrawork.
@@ -222,10 +235,14 @@ Comportamento das tags:
 ## Documentação
 
 - **[Referência Completa](docs/REFERENCE.md)** - Documentação completa de recursos
-- **[Monitoramento de Performance](docs/PERFORMANCE-MONITORING.md)** - Rastreamento de agentes, debugging e otimização
+- **[Referência CLI](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#cli-reference)** - Todos os comandos, flags e ferramentas do `omc`
+- **[Guia de Notificações](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#notifications)** - Configuração de Discord, Telegram, Slack e webhooks
+- **[Workflows Recomendados](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#workflows)** - Cadeias de skills testadas em batalha para tarefas comuns
+- **[Notas de Lançamento](https://yeachan-heo.github.io/oh-my-claudecode-website/docs.html#release-notes)** - Novidades em cada versão
 - **[Website](https://yeachan-heo.github.io/oh-my-claudecode-website)** - Guias interativos e exemplos
 - **[Guia de Migração](docs/MIGRATION.md)** - Upgrade a partir da v2.x
 - **[Arquitetura](docs/ARCHITECTURE.md)** - Como funciona por baixo dos panos
+- **[Monitoramento de Performance](docs/PERFORMANCE-MONITORING.md)** - Rastreamento de agentes, debugging e otimização
 
 ---
 
@@ -255,7 +272,7 @@ MIT
 
 <div align="center">
 
-**Inspirado por:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/NexTechFusion/Superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code)
+**Inspirado por:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) • [claude-hud](https://github.com/ryanjoachim/claude-hud) • [Superpowers](https://github.com/obra/superpowers) • [everything-claude-code](https://github.com/affaan-m/everything-claude-code) • [Ouroboros](https://github.com/Q00/ouroboros)
 
 **Curva de aprendizado zero. Poder máximo.**