Back to Details

omega-cursor-cli

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Cursor CLI Skill

Cursor CLI Skill

<identity> Headless wrapper for Cursor Agent CLI. Passes prompt as last positional arg to `cursor-agent --print --output-format text`. Multi-model routing via --model auto. Requires paid Cursor subscription. </identity> <capabilities> - Headless Cursor Agent CLI invocation with positional prompt - Multi-model routing (auto, claude-4.6-opus, gemini-3.1-pro, gpt-5.3-codex, etc.) - JSON output mode - YOLO mode (auto-approve all tool calls for non-interactive use) - Trust mode (skip workspace trust prompts) - MCP approval mode (--approve-mcps) - Wrapper-level timeout with exit code 124 - Complex Windows PATH resolution (agent, cursor-agent, %LOCALAPPDATA%, npx fallback) - Availability verification </capabilities>
<identity> Cursor Agent CLI的无界面包装器。将提示语作为最后一个位置参数传递给`cursor-agent --print --output-format text`。通过--model auto实现多模型路由。需要付费Cursor订阅。 </identity> <capabilities> - 以位置提示语方式无界面调用Cursor Agent CLI - 多模型路由（auto、claude-4.6-opus、gemini-3.1-pro、gpt-5.3-codex等） - JSON输出模式 - YOLO模式（自动批准所有工具调用，适用于非交互式使用） - 信任模式（跳过工作区信任提示） - MCP批准模式（--approve-mcps） - 包装器级超时，退出码124 - 复杂Windows PATH解析（agent、cursor-agent、%LOCALAPPDATA%、npx备选） - 可用性验证 </capabilities>

Usage

用法

Ask a question (auto model selection)

提问（自动模型选择）

bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "How should I structure this React component?" --yolo --trust
bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "How should I structure this React component?" --yolo --trust

Specific model

指定模型

bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Review this API design" --model claude-4.6-opus --yolo --trust
bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Review this API design" --model claude-4.6-opus --yolo --trust

With timeout

带超时

bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Refactor authentication" --yolo --trust --timeout-ms 180000
bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Refactor authentication" --yolo --trust --timeout-ms 180000

JSON output

JSON输出

bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Generate types" --json --yolo --trust
bash
node .claude/skills/omega-cursor-cli/scripts/ask-cursor.mjs "Generate types" --json --yolo --trust

Availability Check

可用性检查

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

Exit 0 = available (CLI found)

退出码0 = 可用（找到CLI）

Exit 1 = not available

退出码1 = 不可用

undefined
undefined

When to Use

适用场景

  • Multi-model perspective via Cursor's auto routing
  • IDE-aware code generation (Cursor has workspace context)
  • When a non-Claude, non-OpenAI perspective is desired
  • Tasks where Cursor's composer models excel
  • 通过Cursor的自动路由获取多模型视角
  • 感知IDE的代码生成（Cursor具备工作区上下文）
  • 当需要非Claude、非OpenAI的视角时
  • Cursor的composer模型擅长的任务

Iron Laws

铁律

  1. ALWAYS use --yolo --trust for headless mode (otherwise blocks on approval prompts)
  2. NEVER assume CLI is available -- most restrictive subscription requirement
  3. ALWAYS include --timeout-ms for production usage
  4. NEVER attempt to detect subscription status programmatically (not possible)
  5. ALWAYS handle WSL issues on Windows (some configurations require WSL)
  1. 无界面模式下务必使用--yolo --trust（否则会在批准提示处阻塞）
  2. 永远不要假设CLI可用——这是最严格的订阅要求
  3. 生产环境使用时务必包含--timeout-ms
  4. 永远不要尝试通过编程方式检测订阅状态（无法实现）
  5. 务必处理Windows上的WSL问题（部分配置需要WSL）

Anti-Patterns

反模式

Anti-PatternWhy BadCorrect Approach
Running without --yoloBlocks on tool approval promptsAlways pass --yolo
Running without --trustBlocks on workspace trust promptAlways pass --trust
Assuming auto model is availableDepends on subscription tierCheck with cursor-agent --list-models
Hardcoding cursor-agent pathPATH differs across OS/install methodsWrapper handles resolution
Ignoring WSL requirementsSome Windows installs are WSL-onlyDocument in setup instructions
反模式危害原因正确做法
不使用--yolo运行会在工具批准提示处阻塞始终传递--yolo
不使用--trust运行会在工作区信任提示处阻塞始终传递--trust
假设自动模型可用取决于订阅层级使用cursor-agent --list-models检查
硬编码cursor-agent路径不同操作系统/安装方式的PATH不同由包装器处理路径解析
忽略WSL要求部分Windows安装仅支持WSL在设置说明中记录

Scripts

脚本

ScriptPurpose
ask-cursor.mjs
Core headless wrapper -- prompt as last positional arg
parse-args.mjs
Argument parser (--model, --json, --yolo, --trust, --timeout-ms)
verify-setup.mjs
Availability check (multi-path resolution)
format-output.mjs
Output normalization
脚本用途
ask-cursor.mjs
核心无界面包装器——提示语作为最后一个位置参数
parse-args.mjs
参数解析器（--model、--json、--yolo、--trust、--timeout-ms）
verify-setup.mjs
可用性检查（多路径解析）
format-output.mjs
输出标准化

Exit Codes

退出码

CodeMeaning
0Success
1Error (CLI failure, subscription issue)
124Timeout (--timeout-ms exceeded)
代码含义
0成功
1错误（CLI失败、订阅问题）
124超时（超出--timeout-ms设置）

Integration Notes

集成说明

  • Subscription: Cursor Pro or Business required for agent/headless mode
  • Stdin limit: 
    ASK_CURSOR_MAX_STDIN_BYTES
    env var (default 50MB)
  • Available models: claude-4.6-opus, claude-4.6-sonnet, composer-1.5, gemini-3.1-pro, gpt-5.3-codex, auto
  • Platform: Partial cross-platform (WSL issues on some Windows configurations)
  • PATH resolution order: agent -> cursor-agent -> %LOCALAPPDATA%\cursor-agent\cursor-agent.cmd -> npx @cursor/agent
  • 订阅： 无界面/agent模式需要Cursor Pro或Business订阅
  • 标准输入限制： 
    ASK_CURSOR_MAX_STDIN_BYTES
    环境变量（默认50MB）
  • 可用模型： claude-4.6-opus、claude-4.6-sonnet、composer-1.5、gemini-3.1-pro、gpt-5.3-codex、auto
  • 平台： 部分跨平台（部分Windows配置存在WSL问题）
  • PATH解析顺序： agent -> cursor-agent -> %LOCALAPPDATA%\cursor-agent\cursor-agent.cmd -> npx @cursor/agent

Memory Protocol

内存协议

Before work: Read 
.claude/context/memory/learnings.md
After work: Append findings to learnings or issues as needed.
Note: Use 
pnpm search:code
to discover references to this skill codebase-wide.
工作前：读取
.claude/context/memory/learnings.md
工作后：根据需要将发现内容追加到learnings或issues中。
注意：使用
pnpm search:code
可在全代码库中查找此skill的引用。