codex

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Codex Skill Guide

Codex 技能指南

Running a Task

运行任务

Default to
```
gpt-5.2
```
model. Ask the user (via
```
AskUserQuestion
```
) which reasoning effort to use (
```
xhigh
```
,
```
high
```
,
```
medium
```
, or
```
low
```
). User can override model if needed (see Model Options below).
Select the sandbox mode required for the task; default to
```
--sandbox read-only
```
unless edits or network access are necessary.

Assemble the command with the appropriate options:

```
-m, --model <MODEL>
```

--config model_reasoning_effort="<high|medium|low>"

--sandbox <read-only|workspace-write|danger-full-access>

```
--full-auto
```
```
-C, --cd <DIR>
```
```
--skip-git-repo-check
```

Always use --skip-git-repo-check.
When continuing a previous session, use
```
codex exec --skip-git-repo-check resume --last
```
via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort when requesting to resume a session. Resume syntax:
```
echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null
```
. All flags have to be inserted between exec and resume.
IMPORTANT: By default, append
```
2>/dev/null
```
to all
```
codex exec
```
commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.
Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes."

默认使用
```
gpt-5.2
```
模型。通过
```
AskUserQuestion
```
询问用户要使用哪种推理强度（
```
xhigh
```
,
```
high
```
,
```
medium
```
, or
```
low
```
）。如有需要，用户可以覆盖模型设置（见下方的模型选项）。
选择任务所需的沙箱模式；默认使用
```
--sandbox read-only
```
，除非需要编辑或网络访问权限。

组装带有适当选项的命令：

```
-m, --model <MODEL>
```

--config model_reasoning_effort="<high|medium|low>"

--sandbox <read-only|workspace-write|danger-full-access>

```
--full-auto
```
```
-C, --cd <DIR>
```
```
--skip-git-repo-check
```

始终使用
```
--skip-git-repo-check
```
。
当继续之前的会话时，通过标准输入使用
```
codex exec --skip-git-repo-check resume --last
```
。恢复会话时，除非用户明确要求，否则不要使用任何配置标志，例如用户在请求恢复会话时指定了模型或推理强度。恢复语法：
```
echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null
```
。所有标志必须插入在exec和resume之间。
重要提示：默认情况下，在所有
```
codex exec
```
命令后追加
```
2>/dev/null
```
以抑制思考令牌（stderr）。仅当用户明确要求查看思考令牌或需要调试时才显示stderr内容。
运行命令，捕获标准输出/标准错误（按适当方式过滤），并向用户总结结果。
Codex完成后，告知用户："您可以随时通过说‘codex resume’或要求我继续进行额外分析或更改来恢复此Codex会话。"

Quick Reference

快速参考

Use case	Sandbox mode	Key flags
Read-only review or analysis	`read-only`	`--sandbox read-only 2>/dev/null`
Apply local edits	`workspace-write`	`--sandbox workspace-write --full-auto 2>/dev/null`
Permit network or broad access	`danger-full-access`	`--sandbox danger-full-access --full-auto 2>/dev/null`
Resume recent session	Inherited from original	`echo "prompt" \| codex exec --skip-git-repo-check resume --last 2>/dev/null` (no flags allowed)
Run from another directory	Match task needs	`-C <DIR>` plus other flags `2>/dev/null`

使用场景	沙箱模式	关键标志
只读审查或分析	`read-only`	`--sandbox read-only 2>/dev/null`
应用本地编辑	`workspace-write`	`--sandbox workspace-write --full-auto 2>/dev/null`
允许网络或全面访问	`danger-full-access`	`--sandbox danger-full-access --full-auto 2>/dev/null`
恢复最近会话	继承自原始会话	`echo "prompt" \| codex exec --skip-git-repo-check resume --last 2>/dev/null` （不允许使用任何标志）
从其他目录运行	匹配任务需求	`-C <DIR>` 加上其他标志 `2>/dev/null`

Model Options

模型选项

Model	Best for	Context window	Key features
`gpt-5.2-max`	Max model: Ultra-complex reasoning, deep problem analysis	400K input / 128K output	76.3% SWE-bench, adaptive reasoning, $1.25/$10.00
`gpt-5.2` ⭐	Flagship model: Software engineering, agentic coding workflows	400K input / 128K output	76.3% SWE-bench, adaptive reasoning, $1.25/$10.00
`gpt-5.2-mini`	Cost-efficient coding (4x more usage allowance)	400K input / 128K output	Near SOTA performance, $0.25/$2.00
`gpt-5.1-thinking`	Ultra-complex reasoning, deep problem analysis	400K input / 128K output	Adaptive thinking depth, runs 2x slower on hardest tasks

GPT-5.2 Advantages: 76.3% SWE-bench (vs 72.8% GPT-5), 30% faster on average tasks, better tool handling, reduced hallucinations, improved code quality. Knowledge cutoff: September 30, 2024.

Reasoning Effort Levels:

```
xhigh
```
- Ultra-complex tasks (deep problem analysis, complex reasoning, deep understanding of the problem)
```
high
```
- Complex tasks (refactoring, architecture, security analysis, performance optimization)
```
medium
```
- Standard tasks (refactoring, code organization, feature additions, bug fixes)
```
low
```
- Simple tasks (quick fixes, simple changes, code formatting, documentation)

Cached Input Discount: 90% off ($0.125/M tokens) for repeated context, cache lasts up to 24 hours.

模型	最佳适用场景	上下文窗口	关键特性
`gpt-5.2-max`	最大模型：超复杂推理、深度问题分析	400K输入 / 128K输出	76.3% SWE-bench得分、自适应推理、价格$1.25/$10.00
`gpt-5.2` ⭐	旗舰模型：软件工程、智能体编码工作流	400K输入 / 128K输出	76.3% SWE-bench得分、自适应推理、价格$1.25/$10.00
`gpt-5.2-mini`	高性价比编码（4倍使用额度）	400K输入 / 128K输出	接近最先进性能、价格$0.25/$2.00
`gpt-5.1-thinking`	超复杂推理、深度问题分析	400K输入 / 128K输出	自适应思考深度、在最难任务上运行速度慢2倍

GPT-5.2优势：76.3% SWE-bench得分（对比GPT-5的72.8%）、平均任务速度快30%、工具处理能力更强、幻觉减少、代码质量提升。知识截止日期：2024年9月30日。

推理强度级别:

```
xhigh
```
- 超复杂任务（深度问题分析、复杂推理、对问题的深度理解）
```
high
```
- 复杂任务（重构、架构设计、安全分析、性能优化）
```
medium
```
- 标准任务（重构、代码组织、功能添加、bug修复）
```
low
```
- 简单任务（快速修复、简单修改、代码格式化、文档编写）

缓存输入折扣: 重复上下文可享受90%折扣（$0.125/百万令牌），缓存有效期最长24小时。

Following Up

后续操作

After every
```
codex
```
command, immediately use
```
AskUserQuestion
```
to confirm next steps, collect clarifications, or decide whether to resume with
```
codex exec resume --last
```
.
When resuming, pipe the new prompt via stdin:
```
echo "new prompt" | codex exec resume --last 2>/dev/null
```
. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.
Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.

每次执行
```
codex
```
命令后，立即使用
```
AskUserQuestion
```
确认下一步操作、收集澄清信息，或决定是否使用
```
codex exec resume --last
```
恢复会话。
恢复会话时，通过标准输入传递新提示：
```
echo "new prompt" | codex exec resume --last 2>/dev/null
```
。恢复的会话会自动使用原始会话的模型、推理强度和沙箱模式。
提出后续操作时，重申所选的模型、推理强度和沙箱模式。

Error Handling

错误处理

Stop and report failures whenever
```
codex --version
```
or a
```
codex exec
```
command exits non-zero; request direction before retrying.
Before you use high-impact flags (
```
--full-auto
```
,
```
--sandbox danger-full-access
```
,
```
--skip-git-repo-check
```
) ask the user for permission using AskUserQuestion unless it was already given.
When output includes warnings or partial results, summarize them and ask how to adjust using
```
AskUserQuestion
```
.

当
```
codex --version
```
或
```
codex exec
```
命令执行失败（退出码非零）时，立即停止并报告失败，在重试前请求用户指示。
使用高影响标志（
```
--full-auto
```
、
```
--sandbox danger-full-access
```
、
```
--skip-git-repo-check
```
）之前，除非用户已明确授权，否则需使用AskUserQuestion请求用户许可。
当输出包含警告或部分结果时，总结这些内容并使用AskUserQuestion询问用户如何调整。

CLI Version

CLI版本

Requires Codex CLI v0.57.0 or later for GPT-5.2 model support. The CLI defaults to

gpt-5.2

on macOS/Linux and

gpt-5.2

on Windows. Check version:

codex --version

Use

/model

slash command within a Codex session to switch models, or configure default in

~/.codex/config.toml

需要Codex CLI v0.57.0或更高版本以支持GPT-5.2模型。macOS/Linux和Windows系统上的CLI默认均使用

gpt-5.2

。检查版本：

codex --version

在Codex会话中使用

/model

斜杠命令切换模型，或在

~/.codex/config.toml

中配置默认模型。