omx

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

oh-my-codex (OMX) - Multi-Agent Orchestration for Codex CLI

oh-my-codex (OMX) - 为Codex CLI打造的多Agent编排系统

When to use this skill

适用场景

Orchestrating complex multi-agent workflows with OpenAI Codex CLI
Running parallel team workers in tmux for coordinated task execution
Using persistent MCP servers for state, memory, and code intelligence
Executing staged pipelines (plan → prd → exec → verify → fix)
Leveraging role-based agent prompts for specialized tasks

通过OpenAI Codex CLI编排复杂的多Agent工作流
在tmux中运行并行团队Worker以协同执行任务
使用持久化MCP服务器管理状态、内存与代码智能
执行分阶段流水线（规划→PRD→执行→验证→修复）
利用基于角色的Agent提示词完成专业任务

1. Core Concepts

1. 核心概念

Role Prompts (30 Agents)

角色提示词（30个Agent）

Agent Tier	Agents	Use Case
Core Development	architect, planner, executor, debugger, verifier, explore	Main development workflow
Quality Assurance	style-reviewer, quality-reviewer, api-reviewer, security-reviewer, performance-reviewer	Code review lane
Domain Experts	dependency-expert, test-engineer, build-fixer, designer, writer, qa-tester	Specialized tasks
Product Strategy	product-manager, ux-researcher, product-analyst, information-architect	Product planning

Agent层级	包含Agent	适用场景
核心开发类	architect, planner, executor, debugger, verifier, explore	主要开发工作流
质量保障类	style-reviewer, quality-reviewer, api-reviewer, security-reviewer, performance-reviewer	代码评审环节
领域专家类	dependency-expert, test-engineer, build-fixer, designer, writer, qa-tester	专业任务处理
产品策略类	product-manager, ux-researcher, product-analyst, information-architect	产品规划工作

Workflow Skills (40+)

工作流技能（40+种）

Skill	Trigger	Description
`autopilot`	`$autopilot`	Full autonomous execution from idea to working code
`ralph`	`$ralph`	Self-referential loop with verifier verification until completion
`ultrawork`	`$ulw`	Maximum parallelism with parallel agent orchestration
`team`	`$team`	N coordinated agents using Codex CLI native teams
`plan`	`$plan`	Strategic planning with consensus and review modes
`research`	`$research`	Parallel scientist agents for comprehensive research
`tdd`	`$tdd`	Test-first development with red-green-refactor cycle
`build-fix`	`$build-fix`	Fix build errors, type errors, and toolchain failures
`code-review`	`$code-review`	Comprehensive code review across all quality dimensions
`security-review`	`$security-review`	Security audit focusing on vulnerabilities and trust boundaries
`cancel`	`$cancel`	Stop execution modes and clear active state

技能	触发指令	说明
`autopilot`	`$autopilot`	从需求到可运行代码的全自主执行
`ralph`	`$ralph`	结合验证器的自循环执行，直至任务完成
`ultrawork`	`$ulw`	最大化并行度的多Agent编排
`team`	`$team`	使用Codex CLI原生团队功能的N个协同Agent
`plan`	`$plan`	支持共识与评审模式的战略规划
`research`	`$research`	由并行科学家Agent完成全面调研
`tdd`	`$tdd`	遵循红-绿-重构循环的测试优先开发
`build-fix`	`$build-fix`	修复构建错误、类型错误与工具链故障
`code-review`	`$code-review`	覆盖全质量维度的全面代码评审
`security-review`	`$security-review`	聚焦漏洞与信任边界的安全审计
`cancel`	`$cancel`	停止执行模式并清除活跃状态

MCP Servers

MCP服务器

Server	Purpose
`omx_state`	Persistent mode lifecycle state
`omx_memory`	Memory + notepad surfaces for long-running sessions
`omx_code_intel`	Code intelligence and context
`omx_trace`	Execution tracing and debugging

服务器	用途
`omx_state`	持久化模式生命周期状态
`omx_memory`	长会话的内存与记事本存储
`omx_code_intel`	代码智能与上下文管理
`omx_trace`	执行追踪与调试

2. Installation & Setup

2. 安装与配置

Prerequisites

前置要求

macOS or Linux (Windows via WSL2)
Node.js >= 20
Codex CLI installed (
```
npm install -g @openai/codex
```
)
Codex auth configured

macOS或Linux（Windows需通过WSL2）
Node.js >= 20
已安装Codex CLI（
```
npm install -g @openai/codex
```
）
已配置Codex身份验证

Install oh-my-codex

安装oh-my-codex

bash

npm install -g oh-my-codex
omx setup
omx doctor

bash

npm install -g oh-my-codex
omx setup
omx doctor

Recommended Launch Profile

Trusted environment with high reasoning

高推理能力的可信环境

omx --xhigh --madmax

---

omx --xhigh --madmax

---

3. Usage Patterns

3. 使用模式

Role Prompts (Inside Codex)

角色提示词（Codex内使用）

text

/prompts:architect "analyze current auth boundaries"
/prompts:executor "implement input validation in login"
/prompts:security-reviewer "audit OAuth flow"

text

/prompts:architect "分析当前认证边界"
/prompts:executor "在登录功能中实现输入验证"
/prompts:security-reviewer "审计OAuth流程"

Workflow Skills

工作流技能

text

$plan "ship OAuth callback safely"
$autopilot "implement user registration"
$team 3:executor "fix all TypeScript errors"

text

$plan "安全交付OAuth回调功能"
$autopilot "实现用户注册功能"
$team 3:executor "修复所有TypeScript错误"

Team Mode (Terminal)

团队模式（终端中使用）

bash

undefined

bash

undefined

Start parallel team workers

启动并行团队Worker

omx team 4:executor "parallelize a multi-module refactor"

omx team 4:executor "多模块重构并行化"

Monitor team status

监控团队状态

omx team status <team-name>

Resume team work

恢复团队工作

omx team resume <team-name>

Shutdown team

终止团队

omx team shutdown <team-name>

---

omx team shutdown <team-name>

---

4. Launch Flags

4. 启动参数

Flag	Description
`--yolo`	Fast execution, minimal verification
`--high`	High reasoning effort
`--xhigh`	Extra-high reasoning effort
`--madmax`	Maps to Codex `--dangerously-bypass-approvals-and-sandbox`
`--force`	Force operation
`--dry-run`	Preview without execution
`--verbose`	Verbose output

参数	说明
`--yolo`	快速执行，最小化验证
`--high`	高推理算力消耗
`--xhigh`	超高推理算力消耗
`--madmax`	对应Codex的 `--dangerously-bypass-approvals-and-sandbox` 参数
`--force`	强制执行操作
`--dry-run`	预览执行过程，不实际运行
`--verbose`	详细输出日志

5. Staged Pipeline

5. 分阶段流水线

OMX implements a structured execution pipeline:

team-plan → team-prd → team-exec → team-verify → team-fix

Plan: Strategic decomposition of work
PRD: Product requirements definition
Exec: Parallel execution by team workers
Verify: Validation of deliverables
Fix: Automated error resolution

OMX实现了结构化的执行流水线：

team-plan → team-prd → team-exec → team-verify → team-fix

规划：对工作进行战略分解
PRD：定义产品需求
执行：由团队Worker并行执行任务
验证：校验交付成果
修复：自动解决错误

6. Hook Extensions (v0.4.0+)

6. 钩子扩展（v0.4.0及以上版本）

Native Lifecycle Events

原生生命周期事件

```
session-start
```
/
```
session-end
```
/
```
session-idle
```
```
turn-complete
```

```
session-start
```
/
```
session-end
```
/
```
session-idle
```
```
turn-complete
```

Plugin Workflow

插件工作流

bash

undefined

bash

undefined

Enable hook plugins

启用钩子插件

OMX_HOOK_PLUGINS=1 omx hooks test

Hook commands

钩子命令

omx hooks init # Initialize hooks omx hooks status # Check hook status omx hooks validate # Validate configuration omx hooks test # Test hook execution


Plugin files: `.omx/hooks/*.mjs`

---

omx hooks init # 初始化钩子 omx hooks status # 检查钩子状态 omx hooks validate # 验证配置 omx hooks test # 测试钩子执行


插件文件路径：`.omx/hooks/*.mjs`

---

7. Configuration

7. 配置

AGENTS.md Injection

AGENTS.md注入

By default, OMX injects project-level AGENTS.md:

bash

-c model_instructions_file="<cwd>/AGENTS.md"

默认情况下，OMX会注入项目级别的AGENTS.md文件：

bash

-c model_instructions_file="<cwd>/AGENTS.md"

Environment Controls

环境变量控制

bash

undefined

bash

undefined

Disable AGENTS.md injection

禁用AGENTS.md注入

OMX_BYPASS_DEFAULT_SYSTEM_PROMPT=0 omx

Custom instructions file

自定义指令文件

OMX_MODEL_INSTRUCTIONS_FILE=/path/to/instructions.md omx

---

OMX_MODEL_INSTRUCTIONS_FILE=/path/to/instructions.md omx

---

Quick Reference

快速参考

Command	Action
`omx`	Launch Codex with HUD
`omx setup`	Install prompts, skills, config wiring
`omx doctor`	Installation/runtime diagnostics
`omx doctor --team`	Team/swarm diagnostics
`omx team <n>:<role> "<task>"`	Start team workers
`omx team status <name>`	Show team status
`omx team shutdown <name>`	Shutdown team
`omx status`	Show active modes
`omx cancel`	Cancel execution modes
`omx reasoning <mode>`	Set reasoning (low/medium/high/xhigh)
`omx hud`	HUD display options
`omx help`	Show help

命令	作用
`omx`	启动带HUD的Codex
`omx setup`	安装提示词、技能与配置
`omx doctor`	安装/运行时诊断
`omx doctor --team`	团队/集群诊断
`omx team <n>:<role> "<task>"`	启动团队Worker
`omx team status <name>`	查看团队状态
`omx team shutdown <name>`	终止团队
`omx status`	查看活跃模式
`omx cancel`	取消执行模式
`omx reasoning <mode>`	设置推理级别（low/medium/high/xhigh）
`omx hud`	HUD显示选项
`omx help`	查看帮助

Resources

资源

Website: https://yeachan-heo.github.io/oh-my-codex-website/
GitHub: https://github.com/Yeachan-Heo/oh-my-codex
npm: https://www.npmjs.com/package/oh-my-codex

官网: https://yeachan-heo.github.io/oh-my-codex-website/
GitHub: https://github.com/Yeachan-Heo/oh-my-codex
npm: https://www.npmjs.com/package/oh-my-codex

License

许可证

MIT License

omx

Original

Translation

oh-my-codex (OMX) - Multi-Agent Orchestration for Codex CLI

oh-my-codex (OMX) - 为Codex CLI打造的多Agent编排系统

When to use this skill

适用场景

1. Core Concepts

1. 核心概念

Role Prompts (30 Agents)

角色提示词（30个Agent）

Workflow Skills (40+)

工作流技能（40+种）

MCP Servers

MCP服务器

2. Installation & Setup

2. 安装与配置

Prerequisites

前置要求

Install oh-my-codex

安装oh-my-codex

Recommended Launch Profile

推荐启动配置

Trusted environment with high reasoning

高推理能力的可信环境

3. Usage Patterns

3. 使用模式

Role Prompts (Inside Codex)

角色提示词（Codex内使用）

Workflow Skills

工作流技能

Team Mode (Terminal)

团队模式（终端中使用）

Start parallel team workers

启动并行团队Worker

Monitor team status

监控团队状态

Resume team work

恢复团队工作

Shutdown team

终止团队

4. Launch Flags

4. 启动参数

5. Staged Pipeline

5. 分阶段流水线

6. Hook Extensions (v0.4.0+)

6. 钩子扩展（v0.4.0及以上版本）

Native Lifecycle Events

原生生命周期事件

Plugin Workflow

插件工作流

Enable hook plugins

启用钩子插件

Hook commands

钩子命令

7. Configuration

7. 配置

AGENTS.md Injection

AGENTS.md注入

Environment Controls

环境变量控制

Disable AGENTS.md injection

禁用AGENTS.md注入

Custom instructions file

自定义指令文件

Quick Reference

快速参考

Resources

资源

License

许可证