omega-codex-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Codex CLI Skill

Codex CLI 技能

Headless wrapper for OpenAI Codex CLI. Passes prompt as positional arg to

codex exec "PROMPT"

. Optimized for code generation and analysis. Requires OPENAI_API_KEY.

OpenAI Codex CLI的无界面封装工具，将提示词作为位置参数传递给

codex exec "PROMPT"

。针对代码生成和分析做了优化，需要配置OPENAI_API_KEY。

When to Use

适用场景

Code generation tasks needing OpenAI/GPT model perspective
Cross-validation of code solutions with a non-Claude model
Tasks benefiting from Codex's code optimization focus
Multi-LLM consultation workflows

需要从OpenAI/GPT模型视角处理的代码生成任务
使用非Claude模型对代码解决方案进行交叉验证
可受益于Codex代码优化能力的任务
多LLM咨询工作流

Usage

使用方法

Ask a question

提问

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Implement a Redis caching layer for Express"

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Implement a Redis caching layer for Express"

With timeout

带超时设置

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Refactor this module" --timeout-ms 120000

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Refactor this module" --timeout-ms 120000

JSONL streaming output

JSONL流式输出

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Generate unit tests" --json

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Generate unit tests" --json

Sandbox mode

沙箱模式

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Write and test a sort algorithm" --sandbox

bash

node .claude/skills/omega-codex-cli/scripts/ask-codex.mjs "Write and test a sort algorithm" --sandbox

Availability Check

可用性检查

bash

node .claude/skills/omega-codex-cli/scripts/verify-setup.mjs

bash

node .claude/skills/omega-codex-cli/scripts/verify-setup.mjs

Exit 0 = available (CLI found + OPENAI_API_KEY set)

退出码 0 = 可用（已找到CLI + 已设置OPENAI_API_KEY）

Exit 1 = not available

退出码 1 = 不可用

undefined

undefined

Scripts

脚本

Script	Purpose
`ask-codex.mjs`	Core headless wrapper — prompt as positional arg
`parse-args.mjs`	Argument parser (--model, --json, --sandbox, --timeout-ms)
`verify-setup.mjs`	Availability check (CLI + OPENAI_API_KEY)
`format-output.mjs`	JSONL event stream normalization

脚本	用途
`ask-codex.mjs`	核心无界面封装工具 — 接收提示词作为位置参数
`parse-args.mjs`	参数解析器（支持--model、--json、--sandbox、--timeout-ms参数）
`verify-setup.mjs`	可用性检查（检查CLI是否存在 + OPENAI_API_KEY是否配置）
`format-output.mjs`	JSONL事件流标准化输出

Flags

参数说明

Flag	Description
`--model MODEL`	Codex model to use
`--json`	JSONL event stream output
`--sandbox`	Workspace-write sandbox mode
`--timeout-ms N`	Timeout in milliseconds (exit code 124 on expiry)

参数	描述
`--model MODEL`	要使用的Codex模型
`--json`	输出JSONL事件流
`--sandbox`	工作区可写沙箱模式
`--timeout-ms N`	超时时间（单位为毫秒，超时后退出码为124）

Exit Codes

退出码说明

Code	Meaning
0	Success
1	Error (CLI failure, auth issue, API error)
124	Timeout (--timeout-ms exceeded)

码值	含义
0	执行成功
1	错误（CLI执行失败、认证问题、API错误）
124	超时（超出--timeout-ms设置的时长）

Anti-Patterns & Iron Laws

反模式与铁律

ALWAYS verify OPENAI_API_KEY is set before invocation
NEVER use stdin for prompt delivery — Codex uses positional arg
ALWAYS include --skip-git-repo-check (built into wrapper)
ALWAYS set --timeout-ms for production usage
NEVER assume --json output is standard JSON — it produces JSONL event stream

调用前务必验证OPENAI_API_KEY已配置
禁止使用标准输入传递提示词 — Codex使用位置参数接收
务必携带--skip-git-repo-check参数（已内置到封装工具中）
生产环境使用时务必设置--timeout-ms参数
不要认为--json输出是标准JSON格式 — 它输出的是JSONL事件流

Integration Notes

集成说明

API key:
```
OPENAI_API_KEY
```
env var required
Rate limits: OpenAI API rate limits apply
Platform: Full cross-platform (Windows uses cmd.exe /d /s /c wrapper)

API密钥： 需要配置
```
OPENAI_API_KEY
```
环境变量
速率限制： 遵循OpenAI API的速率限制规则
平台支持： 完全跨平台（Windows下使用cmd.exe /d /s /c封装运行）

Memory Protocol (MANDATORY)

存储协议（强制要求）

Before starting: Read

.claude/context/memory/learnings.md

After completing:

New pattern ->
```
.claude/context/memory/learnings.md
```
Issue found ->
```
.claude/context/memory/issues.md
```
Decision made ->
```
.claude/context/memory/decisions.md
```

ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

Note: Use
pnpm search:code
to discover references to this skill codebase-wide.

执行前： 读取

.claude/context/memory/learnings.md

执行完成后：

新的模式 -> 写入
```
.claude/context/memory/learnings.md
```
发现的问题 -> 写入
```
.claude/context/memory/issues.md
```
做出的决策 -> 写入
```
.claude/context/memory/decisions.md
```

假设存在中断风险：如果内容没有写入存储，就等于没有发生过。

注意：使用
pnpm search:code
可以检索整个代码库中对该技能的引用。