OMX：OpenAI Codex CLI 多智能体编排工具，实现AI驱动开发工作流自动化

omx by supercent-io/skills-template

414 周安装量

88 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/supercent-io/skills-template --skill omx

AI/机器学习开发自动化

🇨🇳中文介绍

oh-my-codex (OMX) - 用于 Codex CLI 的多智能体编排

何时使用此技能

使用 OpenAI Codex CLI 编排复杂的多智能体工作流
在 tmux 中运行并行团队工作器以协调任务执行
使用持久化的 MCP 服务器处理状态、内存和代码智能
执行分阶段流水线（规划 → 产品需求文档 → 执行 → 验证 → 修复）
利用基于角色的智能体提示来处理专门任务

1. 核心概念

角色提示 (30 个智能体)

智能体层级	智能体	用例
核心开发	architect, planner, executor, debugger, verifier, explore	主要开发工作流
质量保证	style-reviewer, quality-reviewer, api-reviewer, security-reviewer, performance-reviewer	代码审查通道
领域专家	dependency-expert, test-engineer, build-fixer, designer, writer, qa-tester	专门任务
产品策略	product-manager, ux-researcher, product-analyst, information-architect	产品规划

工作流技能 (40+)

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

技能	触发指令	描述
`autopilot`	`$autopilot`	从想法到可运行代码的完全自主执行
`ralph`	`$ralph`	带验证器验证的自引用循环，直至完成
`ultrawork`	`$ulw`	通过并行智能体编排实现最大并行度
`team`	`$team`	使用 Codex CLI 原生团队功能的 N 个协调智能体
`plan`	`$plan`	具有共识和审查模式的战略规划
`research`	`$research`	并行科学家智能体进行综合研究
`tdd`	`$tdd`	采用红-绿-重构循环的测试驱动开发
`build-fix`	`$build-fix`	修复构建错误、类型错误和工具链故障
`code-review`	`$code-review`	跨所有质量维度的综合代码审查
`security-review`	`$security-review`	专注于漏洞和信任边界的安全审计
`cancel`	`$cancel`	停止执行模式并清除活动状态

服务器	用途
`omx_state`	持久化模式生命周期状态
`omx_memory`	用于长时间运行会话的内存 + 记事本界面
`omx_code_intel`	代码智能和上下文
`omx_trace`	执行跟踪和调试

角色提示 (在 Codex 内部)

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

$plan "安全地发布 OAuth 回调"
$autopilot "实现用户注册"
$team 3:executor "修复所有 TypeScript 错误"

团队模式 (终端)

# 启动并行团队工作器
omx team 4:executor "并行化多模块重构"

# 监控团队状态
omx team status <team-name>

# 恢复团队工作
omx team resume <team-name>

# 关闭团队
omx team shutdown <team-name>

标志	描述
`--yolo`	快速执行，最小化验证
`--high`	高推理强度
`--xhigh`	超高推理强度
`--madmax`	映射到 Codex 的 `--dangerously-bypass-approvals-and-sandbox`
`--force`	强制操作
`--dry-run`	预览而不执行
`--verbose`	详细输出

5. 分阶段流水线

OMX 实现了一个结构化的执行流水线：

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

规划 : 工作的战略分解
产品需求文档 : 产品需求定义
执行 : 由团队工作器并行执行
验证 : 交付成果的验证
修复 : 自动错误解决

6. 钩子扩展 (v0.4.0+)

原生生命周期事件

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

# 启用钩子插件
OMX_HOOK_PLUGINS=1 omx hooks test

# 钩子命令
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：.omx/hooks/*.mjs

默认情况下，OMX 会注入项目级别的 AGENTS.md：

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

# 禁用 AGENTS.md 注入
OMX_BYPASS_DEFAULT_SYSTEM_PROMPT=0 omx

# 自定义指令文件
OMX_MODEL_INSTRUCTIONS_FILE=/path/to/instructions.md omx

命令	操作
`omx`	启动带 HUD 的 Codex
`omx setup`	安装提示、技能、配置连接
`omx doctor`	安装/运行时诊断
`omx doctor --team`	团队/集群诊断
`omx team <n>:<role> "<task>"`	启动团队工作器
`omx team status <name>`	显示团队状态
`omx team shutdown <name>`	关闭团队
`omx status`	显示活动模式
`omx cancel`	取消执行模式
`omx reasoning <mode>`	设置推理模式 (low/medium/high/xhigh)
`omx hud`	HUD 显示选项
`omx help`	显示帮助

🇺🇸English

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

When to use this skill

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

1. Core Concepts

Role Prompts (30 Agents)

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

Workflow Skills (40+)

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`

MCP Servers

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

2. Installation & Setup

Prerequisites

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

Install oh-my-codex

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

Recommended Launch Profile

# Trusted environment with high reasoning
omx --xhigh --madmax

3. Usage Patterns

Role Prompts (Inside Codex)

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

Workflow Skills

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

Team Mode (Terminal)

# Start parallel team workers
omx team 4:executor "parallelize a multi-module refactor"

# Monitor team status
omx team status <team-name>

# Resume team work
omx team resume <team-name>

# Shutdown team
omx team shutdown <team-name>

4. Launch Flags

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`

5. Staged Pipeline

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

6. Hook Extensions (v0.4.0+)

Native Lifecycle Events

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

Plugin Workflow

# Enable hook plugins
OMX_HOOK_PLUGINS=1 omx hooks test

# Hook commands
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

7. Configuration

AGENTS.md Injection

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

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

Environment Controls

# Disable AGENTS.md injection
OMX_BYPASS_DEFAULT_SYSTEM_PROMPT=0 omx

# Custom instructions file
OMX_MODEL_INSTRUCTIONS_FILE=/path/to/instructions.md omx

Quick Reference

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

Resources

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

License

MIT License

Weekly Installs

414

Repository

supercent-io/sk…template

GitHub Stars

First Seen

Mar 10, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykWarn

Installed on

gemini-cli362

codex357

opencode342

kimi-cli338

cursor338

github-copilot338

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

138,300 周安装