Skip to content

Commit 629b9ee

Browse files
committed
docs: 加 OpenAI Codex CLI 教程(10 款工具齐了,源码 6 轮核实,中英双语)
新增 codex/ 章节(中英双语 + 4 个模板),把"主流 AI 编程工具"扩到 10 款。 内容对照 codex-rs 源码核实过 6 轮:每条 CLI flag、子命令、slash 命令、 config 字段、subagent schema 都有源码出处。 新增文件: - codex/README.md / README.en.md(712/708 行,含 16 节进阶用法) - codex/templates/AGENTS.md(项目指令文件模板) - codex/templates/config.toml(用户配置 + 4 个 profile) - codex/templates/agent-explorer.toml(只读探索 subagent) - codex/templates/SKILL.md(带触发器写法 + Gotchas) 覆盖 v0.125.0 全部核心能力:AGENTS.md 加载链 / Approval & Sandbox 双旋钮 / TOML Subagent / MCP / Skills(含文件夹结构 + 触发语法)/ Hooks(6 事件, 复用 Claude schema)/ Memories(跨 session)/ Plugin Marketplace / Fast Mode / OSS 本地模型(Ollama/LM Studio)/ 官方 GitHub Action / Codex 作 MCP server / Execpolicy(Starlark DSL)。 源码核实修正了 9 处常见错误: - bubblewrap → Landlock(Linux 实际用的内核 LSM) - --full-auto 已废弃 → --sandbox workspace-write - --output-format json 不存在 → --json(JSONL) - /side 错删 → 实际真实存在并恢复 - web_search 顶层 key(不在 [features] 下) - Memories canonical 字段名 disable_on_external_context - 等 同步索引: - README "9 → 10 款",工具表加 Codex CLI 行 - cheatsheet 能力矩阵加 Codex 列 + 沙箱机制行 + Hook 自动化补 beta - cheatsheet 决策表/命令段/组合推荐全部对齐 - CHANGELOG 双语记录 6 轮源码核实历程
1 parent 1b1a1d6 commit 629b9ee

12 files changed

Lines changed: 1942 additions & 48 deletions

CHANGELOG.en.md

Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,79 @@
44

55
> See `git log` for full commit history. This file records user-facing major updates.
66
7+
## Late April 2026 · OpenAI Codex CLI Guide Added
8+
9+
### 🆕 New Tool: Codex CLI (now 10 tools total)
10+
11+
**📂 [`codex/`](codex/) — OpenAI's open-source terminal agent (Rust, Apache-2.0)**
12+
- Verified against v0.125.0 (2026-04-24) and `developers.openai.com/codex` official docs
13+
- Full coverage: core concepts / install & auth / AGENTS.md discovery chain / Approval & Sandbox dual knobs / TOML subagents / MCP / Skills / Plan Mode
14+
- Side-by-side comparison with Claude Code (sandbox internals, pricing model, sweet spots)
15+
- 10 common pitfalls (CI hangs on approval prompt, config not taking effect, duplicate installs, etc.)
16+
- Templates: `AGENTS.md` + `config.toml` (with 4 profiles) + `agent-explorer.toml`
17+
18+
### 🔄 Index Sync
19+
20+
- **README.md / README.en.md**: "9 tools" → "10 tools", tool table now includes Codex CLI, profile-based reading paths add "Already on ChatGPT Plus/Pro"
21+
- **cheatsheet.md / cheatsheet.en.md**: capability matrix gets a Codex column plus a new "Sandbox" row, config-file table gets AGENTS.md, commands cheat sheet gets a Codex section, decision flow and combo recommendations both updated
22+
23+
### 🔬 Second-pass source-code verification
24+
25+
Before publishing, the guide was cross-checked directly against `codex-rs` source (`utils/cli/src/shared_options.rs`, `tui/src/cli.rs`, `exec/src/cli.rs`, `cli/src/main.rs`, `models-manager/models.json`). Six factual issues were caught and fixed:
26+
27+
1. **Linux sandbox**: `bubblewrap``Landlock` kernel LSM (`debug_sandbox.rs` imports `codex_sandboxing::landlock`)
28+
2. **`--full-auto` removed**: source ships a migration warning *"`--full-auto` is deprecated; use `--sandbox workspace-write` instead."* — every example switched
29+
3. **`--output-format json` does not exist**: the real flag is `--json` (emits JSONL, not a single JSON object)
30+
4. **`/side` does not exist**: never appeared in `slash_commands` docs — removed; replaced with real ones (`/diff`, `/mention`, `/debug-config`, `/new`, `/clear`)
31+
5. **`codex config path` / `codex config validate` do not exist**: there's no `config` subcommand — the right diagnostic is the TUI `/debug-config` slash command
32+
6. **Added `--yolo` and `--add-dir`**: verified in source as the current recommended danger/expansion flags
33+
34+
Model names verified: `gpt-5.5` / `gpt-5.4` / `gpt-5.3-codex` all present in the canonical `models-manager/models.json` list.
35+
36+
### 🔬 Fourth-pass schema-level verification (config / subagent TOML structures)
37+
38+
Cross-checked against the actual Rust struct definitions (`config_toml.rs::ConfigToml`, `profile_toml.rs::ConfigProfile`, `config_toml.rs::AgentsToml/AgentRoleToml`, `core/src/config/agent_roles.rs::RawAgentRoleFileToml`):
39+
40+
- **`web_search` is a top-level key** (valid values `disabled`/`cached`/`live`), not under `[features]`; template fixed
41+
- **`multi_agent` is not a simple `[features]` bool** (multi-agent uses its own `[multi_agent_v2]` structure); template field removed
42+
- **Subagent TOML fields** = `RawAgentRoleFileToml` flattens all of `ConfigToml`, so `name` / `description` / `developer_instructions` / `model` / `model_reasoning_effort` / `sandbox_mode` / `approval_policy` are all valid; `#[serde(deny_unknown_fields)]` rejects typos at startup
43+
- **`model_reasoning_effort` valid values**: `none` / `minimal` / `low` / `medium` (default) / `high` / `xhigh` (source: `protocol/src/openai_models.rs::ReasoningEffort`)
44+
- **`[agents]` concurrency keys**: `max_threads` / `max_depth` / `job_max_runtime_seconds` / `interrupt_message` match the `AgentsToml` struct
45+
- **`AGENTS_MD_MAX_BYTES = 32 * 1024`** (i.e. 32 KiB) — default verified directly in source
46+
47+
### 📚 v2 content expansion (based on high-star community guides)
48+
49+
After studying [RoggeOhta/awesome-codex-cli](https://github.com/RoggeOhta/awesome-codex-cli) (280+ resources) and [shanraisshan/codex-cli-best-practice](https://github.com/shanraisshan/codex-cli-best-practice) (50 battle-tested tips), four real features that v1 missed have been added:
50+
51+
- **Real Skill folder structure**: v1 incorrectly described it as a single `SKILL.md` file; source `core-skills/loader.rs` confirms it's a **directory** with optional `references/`, `scripts/`, `examples/`, `agents/openai.yaml`. Canonical path is `~/.agents/skills/` (`~/.codex/skills/` is deprecated). Added the `$skill-name` explicit invocation syntax.
52+
- **Hooks** (beta): 6 events — `PreToolUse` / `PermissionRequest` / `PostToolUse` / `SessionStart` / `UserPromptSubmit` / `Stop`. Source engine is named `ClaudeHooksEngine` — the JSON schema reuses Claude Code's `hooks.json` directly, zero-change migration.
53+
- **Memories** (beta): `/memories` slash command + `[memories] no_memories_if_mcp_or_web_search` safety toggle.
54+
- **Plugins / Marketplace** (v0.121.0+): `codex plugin marketplace add/upgrade/remove`, TUI `/plugins`.
55+
- **Fast Mode**: `/fast on|off|status`, gpt-5.4 at 1.5× speed / 2× credits.
56+
57+
A new "High-Signal Prompting & Workflow Patterns" section consolidates 5 buckets of community wisdom (prompting / planning / AGENTS.md / multi-agent / debugging). The References section now lists 6 high-star community indexes and 4 mainstream workflow frameworks (Superpowers / Spec Kit / oh-my-codex / Compound Engineering).
58+
59+
New [`templates/SKILL.md`](codex/templates/SKILL.md) template (with trigger-style description + Gotchas pattern).
60+
61+
### 🔬 Sixth-pass source verification + v3 content additions
62+
63+
Read the `codex-rs/tui/src/slash_command.rs::SlashCommand` enum directly (46 real slash commands) and caught a third-pass over-correction:
64+
65+
- **`/side` is a real command** ("start a side conversation in an ephemeral fork") — round 3 incorrectly removed it based on a WebFetch summary; restored
66+
- **`/fast` is in the enum** ("toggle Fast mode to enable fastest inference with increased plan usage") — v2 addition was correct
67+
- **Slash command table expanded to 18 entries**: added `/skills`, `/memories`, `/plugins`, `/apps`, `/goal`, `/rename`, `/feedback`, `/approvals`, etc.
68+
69+
`MemoriesToml` source confirms the canonical field is **`disable_on_external_context`**, with `no_memories_if_mcp_or_web_search` as its serde alias (backward-compat). All docs updated to use the canonical name.
70+
71+
Four new feature sections added (each verified in source):
72+
73+
- **§13 OSS local models**`--oss --local-provider lmstudio|ollama` (from `utils/oss/src/lib.rs`), fully offline + zero API cost
74+
- **§14 Official GitHub Action recipe**`openai/codex-action@v1` (Apache-2.0, 953 stars) with a complete PR-auto-review workflow YAML
75+
- **§15 Codex as an MCP server**`codex mcp-server` exposes `codex()` and `codex-reply()` tools for reverse integration with other agents
76+
- **§16 Rules / Execpolicy** — Starlark DSL (`prefix_rule()` + `host_executable()`), validate offline with `codex execpolicy check`
77+
78+
---
79+
780
## 2026-04 · Major Update: From "Tool Tutorials" to "Full Hands-On Handbook"
881

982
### 🆕 New Modules

CHANGELOG.md

Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,79 @@
22

33
> 完整提交历史见 `git log`。本文档记录面向用户的重要更新。
44
5+
## 2026-04(下半月) · 新增 OpenAI Codex CLI 教程
6+
7+
### 🆕 新增工具:Codex CLI(10 款工具齐了)
8+
9+
**📂 [`codex/`](codex/) — OpenAI 官方开源终端 Agent(Rust,Apache-2.0)**
10+
- 基于 v0.125.0(2026-04-24)+ developers.openai.com/codex 官方文档核实
11+
- 完整覆盖:核心概念 / 安装认证 / AGENTS.md 加载链 / Approval & Sandbox 双旋钮 / TOML Subagent / MCP / Skill / Plan Mode
12+
- 与 Claude Code 横向对比(沙箱实现、定价模式、强项场景)
13+
- 10 个高频踩坑(CI 卡 approval、配置不生效、多版本冲突等)
14+
- 模板:`AGENTS.md` + `config.toml`(含 4 个 profile)+ `agent-explorer.toml`
15+
16+
### 🔄 同步更新
17+
18+
- **README.md / README.en.md**:「9 款工具」→「10 款」,工具表新增 Codex CLI 行,画像推荐路径加入"已订阅 ChatGPT Plus/Pro"
19+
- **cheatsheet.md / cheatsheet.en.md**:能力矩阵新增 Codex 列与「沙箱机制」维度,配置文件表加入 AGENTS.md,命令速查新增 Codex 段,决策流与组合推荐双向更新
20+
21+
### 🔬 二次源码核实修正
22+
23+
教程发布前直接读 `codex-rs` 源码(`utils/cli/src/shared_options.rs``tui/src/cli.rs``exec/src/cli.rs``cli/src/main.rs``models-manager/models.json`)核对,修正 6 处不准确:
24+
25+
1. **Linux 沙箱**`bubblewrap``Landlock` 内核 LSM(`debug_sandbox.rs` 直接 import `codex_sandboxing::landlock`
26+
2. **`--full-auto` 已废弃移除**:源码警告 *"`--full-auto` is deprecated; use `--sandbox workspace-write` instead."*,所有示例统一替换
27+
3. **`--output-format json` 不存在**:实际 flag 是 `--json`(输出 JSONL,不是单 JSON)
28+
4. **`/side` 不存在**:从未在 `slash_commands` 文档里出现,删除;改成真实存在的 `/diff` `/mention` `/debug-config` `/new` `/clear`
29+
5. **`codex config path` / `codex config validate` 不存在**:CLI 没有 `config` 子命令,应该用 TUI 内的 `/debug-config`
30+
6. **新增 `--yolo` / `--add-dir`**:源码确认这两个 flag 是当前推荐的危险/扩展用法
31+
32+
模型名校验:`gpt-5.5` / `gpt-5.4` / `gpt-5.3-codex` 全部命中 `models-manager/models.json` 官方列表。
33+
34+
### 🔬 第四轮 schema 级核实(config / subagent TOML 结构)
35+
36+
直接对照 Rust struct 定义(`config_toml.rs::ConfigToml``profile_toml.rs::ConfigProfile``config_toml.rs::AgentsToml/AgentRoleToml``core/src/config/agent_roles.rs::RawAgentRoleFileToml`):
37+
38+
- **`web_search` 是顶层 key**(合法值 `disabled`/`cached`/`live`),不在 `[features]` 下;template 已修
39+
- **`multi_agent` 不是 features 简单 bool**(多 agent 走 `[multi_agent_v2]` 自有结构);template 已删
40+
- **subagent TOML 字段** = `RawAgentRoleFileToml` flatten 了整个 `ConfigToml`,所以 `name` / `description` / `developer_instructions` / `model` / `model_reasoning_effort` / `sandbox_mode` / `approval_policy` 都合法;`#[serde(deny_unknown_fields)]` 兜底拼错会报错
41+
- **`model_reasoning_effort` 合法值**`none` / `minimal` / `low` / `medium`(默认) / `high` / `xhigh`(来源 `protocol/src/openai_models.rs::ReasoningEffort`
42+
- **`[agents]` 段并发参数**`max_threads` / `max_depth` / `job_max_runtime_seconds` / `interrupt_message` 与源码 `AgentsToml` 结构一致
43+
- **`AGENTS_MD_MAX_BYTES = 32 * 1024`**(即 32 KiB)—— 默认值已直接在源码确认
44+
45+
### 📚 v2 内容补完(基于 GitHub 高 star 实战教程)
46+
47+
参考 [RoggeOhta/awesome-codex-cli](https://github.com/RoggeOhta/awesome-codex-cli)(280+ 资源)和 [shanraisshan/codex-cli-best-practice](https://github.com/shanraisshan/codex-cli-best-practice)(50 条战场技巧)后,补完 4 个原本没覆盖的真实功能:
48+
49+
- **Skills 真实文件夹结构**:原 v1 写成单文件 `SKILL.md`,源码 `core-skills/loader.rs` 确认是 **目录**`references/` `scripts/` `examples/` `agents/openai.yaml`;canonical 路径 `~/.agents/skills/``~/.codex/skills/` 已废弃);新增 `$skill-name` 显式调用语法
50+
- **Hooks**(beta):6 个事件 `PreToolUse` / `PermissionRequest` / `PostToolUse` / `SessionStart` / `UserPromptSubmit` / `Stop`,源码引擎名 `ClaudeHooksEngine`——schema 直接复用 Claude Code 的 `hooks.json`,迁移零改动
51+
- **Memories**(beta):`/memories` slash 命令 + `[memories] no_memories_if_mcp_or_web_search` 安全开关
52+
- **Plugins / Marketplace**(v0.121.0+):`codex plugin marketplace add/upgrade/remove`,TUI `/plugins`
53+
- **Fast Mode**`/fast on|off|status`,gpt-5.4 1.5× 速度 / 2× 额度
54+
55+
新增「高质量提示词与工作模式」整段,集合社区 5 类高信号技巧(提示词 / Plan / AGENTS.md / 多 Agent / 调试),并在 References 段补 6 个高 star 索引和 4 个主流 workflow 框架(Superpowers / Spec Kit / oh-my-codex / Compound Engineering)。
56+
57+
新增 [`templates/SKILL.md`](codex/templates/SKILL.md) 模板(带触发器写法 + Gotchas 范本)。
58+
59+
### 🔬 第六轮源码核实 + v3 内容补完
60+
61+
直接读 `codex-rs/tui/src/slash_command.rs::SlashCommand` 枚举(46 个真实 slash 命令),抓出第三轮的过修正:
62+
63+
- **`/side` 是真实存在的命令**("start a side conversation in an ephemeral fork")—— 第三轮凭 WebFetch 摘要错删,现已恢复
64+
- **`/fast` 也确实在 enum 里**("toggle Fast mode to enable fastest inference with increased plan usage")—— v2 加上是对的
65+
- **slash 命令表扩到 18 条**:补 `/skills` `/memories` `/plugins` `/apps` `/goal` `/rename` `/feedback` `/approvals`
66+
67+
`MemoriesToml` 源码确认 canonical 字段是 **`disable_on_external_context`**`no_memories_if_mcp_or_web_search` 是它的 serde alias(向后兼容),文档全部改用 canonical 名。
68+
69+
新增 4 节真功能(每节都对照源码核实):
70+
71+
- **§13 OSS 本地模型**`--oss --local-provider lmstudio|ollama` (来源 `utils/oss/src/lib.rs`),完全离线 + 零 API 成本
72+
- **§14 官方 GitHub Action 实战**`openai/codex-action@v1`(Apache-2.0,953 stars)的 PR 自动 review 完整 workflow YAML
73+
- **§15 Codex 作为 MCP server**`codex mcp-server` 暴露 `codex()` + `codex-reply()` 工具,让其他 Agent 反向调用
74+
- **§16 Rules / Execpolicy** — Starlark DSL(`prefix_rule()` + `host_executable()`),`codex execpolicy check` 离线验证
75+
76+
---
77+
578
## 2026-04 · 重大更新:从"工具教程"到"完整落地手册"
679

780
### 🆕 新增模块

README.en.md

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# AI Coding Tools — The Practical Guide
22

3-
> **Hands-on best practices for 9 AI coding tools** — No hype, just what works. Prompt techniques, workflow design, multi-tool orchestration, and copy-paste configs to maximize your AI-assisted development.
3+
> **Hands-on best practices for 10 AI coding tools** — No hype, just what works. Prompt techniques, workflow design, multi-tool orchestration, and copy-paste configs to maximize your AI-assisted development.
44
55
[简体中文](./README.md) | **English**
66

@@ -10,7 +10,7 @@
1010

1111
<table>
1212
<tr>
13-
<td align="center"><strong>9 Tools</strong><br/>Full coverage</td>
13+
<td align="center"><strong>10 Tools</strong><br/>Full coverage</td>
1414
<td align="center"><strong>66 Tips</strong><br/>Claude Code deep-dive</td>
1515
<td align="center"><strong>7 Methodologies</strong><br/>Prompting / Debug / Test</td>
1616
<td align="center"><strong>Copy-paste Configs</strong><br/>Ready to use</td>
@@ -21,7 +21,7 @@
2121

2222
## Getting Started
2323

24-
**Start with the [📋 Cheatsheet](cheatsheet.en.md)** — all 9 tools on one page: type, context window, config files, core commands. Know what to pick, how to set it up, how to use it.
24+
**Start with the [📋 Cheatsheet](cheatsheet.en.md)** — all 10 tools on one page: type, context window, config files, core commands. Know what to pick, how to set it up, how to use it.
2525

2626
**Pick a path based on your profile:**
2727

@@ -31,18 +31,20 @@
3131
| Frontend / daily coding | [Cursor](cursor/)[Prompt Engineering](common/prompting.en.md)[Scenarios](workflows/scenarios.en.md) |
3232
| Backend / refactoring / big projects | [Claude Code](claude-code/)[Task Decomposition](common/task-decomposition.en.md)[Scenarios](workflows/scenarios.en.md) |
3333
| Migrating from Copilot | [Copilot](copilot/)[Claude Code](claude-code/) (compare) → [Tool Selection](workflows/tool-selection.en.md) |
34+
| Already on ChatGPT Plus/Pro | [Codex CLI](codex/)[Claude Code](claude-code/) (compare) → [Tool Selection](workflows/tool-selection.en.md) |
3435
| Cost-conscious / solo dev | [Cheatsheet](cheatsheet.en.md)[Gemini CLI](gemini-cli/) or [Aider](aider/) + local models |
3536
| Team / high-quality delivery | [Kiro](kiro/)[Code Review](common/code-review.en.md)[Testing](common/testing.en.md) |
3637

3738
**Already using AI tools?** Jump to: [Cheatsheet](cheatsheet.en.md) · [Advanced Tips](#9-tool-guides) · [Real-World Workflows](#real-world-workflows) · [Ecosystem](#ecosystem)
3839

3940
---
4041

41-
## 9 Tool Guides
42+
## 10 Tool Guides
4243

4344
| Tool | Type | Highlights |
4445
|------|------|-----------|
4546
| [**Claude Code**](claude-code/README.en.md) | CLI Agent | 66 tips, Agent + Skill + Hook workflows |
47+
| [**Codex CLI**](codex/README.en.md) | CLI Agent | OpenAI's open-source (Rust), Sandbox + AGENTS.md, ChatGPT-plan friendly |
4648
| [**Cursor**](cursor/README.en.md) | IDE | .cursorrules config, Composer Agent mode |
4749
| [**GitHub Copilot**](copilot/README.en.md) | IDE Plugin | Inline completion + Agent mode + custom instructions |
4850
| [**OpenClaw**](openclaw/README.en.md) | AI Agent Framework | 338k Stars, multi-platform + Skills + Cron automation |

README.md

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -2,15 +2,15 @@
22

33
**简体中文** | [English](./README.en.md)
44

5-
> **9 款主流 AI 编程工具的中文最佳实践** — 不讲概念,只讲怎么用好。从提示词技巧到工作流设计,从单工具精通到多工具协作,帮你把 AI 编程效率拉满。
5+
> **10 款主流 AI 编程工具的中文最佳实践** — 不讲概念,只讲怎么用好。从提示词技巧到工作流设计,从单工具精通到多工具协作,帮你把 AI 编程效率拉满。
66
77
[![GitHub stars](https://img.shields.io/github/stars/jnMetaCode/ai-coding-guide?style=social)](https://github.com/jnMetaCode/ai-coding-guide)
88
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](./LICENSE)
99
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://makeapullrequest.com)
1010

1111
<table>
1212
<tr>
13-
<td align="center"><strong>9 款工具</strong><br/>全覆盖教程</td>
13+
<td align="center"><strong>10 款工具</strong><br/>全覆盖教程</td>
1414
<td align="center"><strong>66 个技巧</strong><br/>Claude Code 深度</td>
1515
<td align="center"><strong>7 套方法论</strong><br/>提示词/调试/测试</td>
1616
<td align="center"><strong>可复制模板</strong><br/>即装即用配置</td>
@@ -21,7 +21,7 @@
2121

2222
## 🚀 快速开始
2323

24-
**先看一眼 [📋 速查表](cheatsheet.md)**9 款工具一页横向对比:类型、上下文、配置文件、常用命令。知道自己选哪个、怎么配、怎么用。
24+
**先看一眼 [📋 速查表](cheatsheet.md)**10 款工具一页横向对比:类型、上下文、配置文件、常用命令。知道自己选哪个、怎么配、怎么用。
2525

2626
**按画像走推荐路径:**
2727

@@ -31,18 +31,20 @@
3131
| 前端 / 日常编码为主 | [Cursor](cursor/)[提示词工程](common/prompting.md)[实战场景](workflows/scenarios.md) |
3232
| 后端 / 重构 / 大项目 | [Claude Code](claude-code/)[需求拆解](common/task-decomposition.md)[实战场景](workflows/scenarios.md) |
3333
| 从 Copilot 迁来 | [Copilot](copilot/)[Claude Code](claude-code/)(对比差异)→ [多工具选型](workflows/tool-selection.md) |
34+
| 已订阅 ChatGPT Plus/Pro | [Codex CLI](codex/)[Claude Code](claude-code/) 对比 → [多工具选型](workflows/tool-selection.md) |
3435
| 控成本 / 独立开发者 | [速查表](cheatsheet.md)[Gemini CLI](gemini-cli/)[Aider](aider/) + 本地模型 |
3536
| 团队协作 / 高质量交付 | [Kiro](kiro/)[代码审查](common/code-review.md)[测试策略](common/testing.md) |
3637

3738
**已经在用了?** 直接看:[速查表](cheatsheet.md) · [进阶技巧](#-9-款工具教程) · [实战工作流](#-实战工作流) · [生态项目](#-相关项目)
3839

3940
---
4041

41-
## 🔧 9 款工具教程
42+
## 🔧 10 款工具教程
4243

4344
| 工具 | 类型 | 亮点 |
4445
|------|------|------|
4546
| [**Claude Code**](claude-code/) | CLI Agent | 66 个技巧,Agent + Skill + Hook 完整工作流 |
47+
| [**Codex CLI**](codex/) | CLI Agent | OpenAI 官方开源(Rust),Sandbox + AGENTS.md,ChatGPT 订阅可用 |
4648
| [**Cursor**](cursor/) | IDE | .cursorrules 配置,Composer Agent 模式 |
4749
| [**GitHub Copilot**](copilot/) | IDE 插件 | 行内补全 + Agent 模式 + 自定义指令 |
4850
| [**OpenClaw**](openclaw/) | AI Agent 框架 | 338k Stars,多平台连接 + Skills + Cron 自动化 |

0 commit comments

Comments
 (0)