Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Operate Code Vscode Ide Node

ASecurity

Operate on code through a VS Code/Cursor IDE connected as an OpenClaw Node. Provides 40+ commands for file operations, language intelligence, git, testing, debugging, and Cursor Agent CLI integration. Use when you need to read/write/edit code, navigate definitions/references, ru…

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgonodetestingdebugginggitapisecurity

Works with

cursorvscodeterminalcliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill operate-code-vscode-ide-node --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Operate Code Vscode Ide Node?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Operate Code Vscode Ide Node
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-operate-code-vscode-ide-node/badge)](https://www.skillsdirectory.com/skills/rondoflow-operate-code-vscode-ide-node)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: operate-code-vscode-ide-node
description: "Operate on code through a VS Code/Cursor IDE connected as an OpenClaw Node. Provides 40+ commands for file operations, language intelligence, git, testing, debugging, and Cursor Agent CLI integration. Use when you need to read/write/edit code, navigate definitions/references, ru…"
category: "AI & Agents"
author: community
version: "1.0.2"
icon: bot
---

# VS Code / Cursor Node Skill

Control a VS Code or Cursor IDE remotely through the OpenClaw Node protocol.

## Related

- **[OpenClaw Node for VS Code](https://marketplace.visualstudio.com/items?itemName=xiaoyaner.openclaw-node-vscode)** — The VS Code/Cursor extension you need to install (required)
- **[cursor-ide-agent](https://clawhub.ai/xiaoyaner0201/cursor-ide-agent)** — Combined skill with both CLI and Node paths (install this instead if you also use Cursor CLI)
- **Source**: [github.com/xiaoyaner-home/openclaw-vscode](https://github.com/xiaoyaner-home/openclaw-vscode)

## Prerequisites

- Extension `openclaw-node-vscode` installed and connected (status bar 🟢)
- Node visible in `nodes status`
- Commands in Gateway's `allowCommands` whitelist

## Invocation Pattern

```
nodes invoke --node "<name>" --invokeCommand "<cmd>" --invokeParamsJson '{"key":"val"}'
```

Both `invokeTimeoutMs` (Gateway internal) and `timeoutMs` (HTTP layer, must be larger) are required for long operations.

**Timeout guide:**

| Type | invokeTimeoutMs | timeoutMs |
|------|----------------|-----------|
| File/editor/lang | 15000 | 20000 |
| Git | 30000 | 35000 |
| Test | 60000 | 65000 |
| Agent plan/ask | 180000 | 185000 |
| Agent run | 300000 | 305000 |

## Command Categories

| Category | Prefix | Key Commands | Reference |
|----------|--------|-------------|-----------|
| **File** | `vscode.file.*` | read, write, edit, delete | [commands/file.md](references/commands/file.md) |
| **Directory** | `vscode.dir.*` | list | [commands/file.md](references/commands/file.md) |
| **Language** | `vscode.lang.*` | definition, references, hover, symbols, rename, codeActions, format | [commands/language.md](references/commands/language.md) |
| **Editor** | `vscode.editor.*` | active, openFiles, selections | [commands/editor.md](references/commands/editor.md) |
| **Diagnostics** | `vscode.diagnostics.*` | get | [commands/editor.md](references/commands/editor.md) |
| **Git** | `vscode.git.*` | status, diff, log, blame, stage, commit, stash | [commands/git.md](references/commands/git.md) |
| **Test** | `vscode.test.*` | list, run, results | [commands/test-debug.md](references/commands/test-debug.md) |
| **Debug** | `vscode.debug.*` | launch, stop, breakpoint, evaluate, stackTrace, variables | [commands/test-debug.md](references/commands/test-debug.md) |
| **Terminal** | `vscode.terminal.*` | run (disabled by default) | [commands/terminal.md](references/commands/terminal.md) |
| **Agent** | `vscode.agent.*` | status, run, setup (Cursor only) | [commands/agent.md](references/commands/agent.md) |
| **Workspace** | `vscode.workspace.*` | info | [commands/editor.md](references/commands/editor.md) |

## Quick Examples

### Read a file
```
nodes invoke --node "my-vscode" --invokeCommand "vscode.file.read" --invokeParamsJson '{"path":"src/main.ts"}'
→ { content, totalLines, language }
```

### Find all references
```
nodes invoke --node "my-vscode" --invokeCommand "vscode.lang.references" --invokeParamsJson '{"path":"src/main.ts","line":10,"character":5}'
→ { locations: [{ path, line, character }] }
```

### Git status + commit
```
nodes invoke --node "my-vscode" --invokeCommand "vscode.git.status"
→ { branch, staged, modified, untracked, ahead, behind }

nodes invoke --node "my-vscode" --invokeCommand "vscode.git.stage" --invokeParamsJson '{"paths":["src/main.ts"]}'
nodes invoke --node "my-vscode" --invokeCommand "vscode.git.commit" --invokeParamsJson '{"message":"fix: resolve type error"}'
```

### Delegate to Cursor Agent
```
nodes invoke --node "my-vscode" --invokeCommand "vscode.agent.run" --invokeParamsJson '{"prompt":"Add error handling to all API endpoints","mode":"plan"}' --invokeTimeoutMs 180000 --timeoutMs 185000
→ { output, exitCode }
```

## Common Workflows

See [references/workflows.md](references/workflows.md) for detailed step-by-step workflows:
- Fix a type error
- Safe cross-file refactor
- Delegate complex task to Cursor Agent

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| `node command not allowed` | Not in Gateway whitelist | Add to `gateway.nodes.allowCommands` |
| `node not found` | Extension not connected | Check extension status bar |
| `timeout` | Operation too long | Increase both timeout params |
| `path traversal blocked` | Path outside workspace | Use relative paths only |
| `read-only mode` | Extension in read-only | Disable `openclaw.readOnly` setting |

## Security

- All paths are **relative to workspace root** — absolute paths and `../` blocked
- Writes respect `readOnly` and `confirmWrites` extension settings
- Terminal disabled by default, whitelist-only when enabled
- Each device has unique Ed25519 identity, must be approved by Gateway

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →