cursor-agent

Low
by swiftlysingh | Audited: 2026-02-26T09:59:20.936Z | Ruleset: 0.2.0

Quick Install

Add this skill to your agent

clawhub install cursor-agent

About This Skill

A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).

Add to PATH in ~/.zshrc (zsh) or ~/.bashrc (bash):
Restart terminal or run source ~/.zshrc (or ~/.bashrc)
Requires macOS 10.15 or later
Works on both Intel and Apple Silicon Macs
Restart your terminal or source your shell config
Commands: agent (primary) and cursor-agent (backward compatible)
List sessions: agent ls
Resume most recent: agent resume

Use Cases

1 Verify with agent --version
2 Verify installation: agent --version or cursor-agent --version
3 Resume specific session: agent --resume="[chat-id]"
4 **/rules** - Create and edit rules directly from CLI
5 **/commands** - Create and modify custom commands
6 **Shift+Enter** - Add newlines for multi-line prompts

Documentation (Original)

Source: README.md
The following is the author's original documentation (often English). For installation, follow “Quick Install” above.

Cursor CLI Agent Skill

This repository contains the definition and documentation for the cursor-agent skill, updated for 2026 features.

Overview

The cursor-agent skill encapsulates workflows and commands for the Cursor CLI, enabling efficient AI-pair programming directly from the terminal. This skill includes all modern features from the January 2026 update.

What's New in v2.0.0

  • Model Switching: Switch between AI models with agent models, --model flag, and /models command
  • MCP Management: Enable/disable MCP servers on the fly with /mcp enable and /mcp disable
  • Rules & Commands: Create and edit rules directly from CLI with /rules and /commands
  • Modern Command Interface: Use agent as the primary command (backward compatible with cursor-agent)
  • Enhanced Headless Mode: New flags including --force, --output-format json, and --stream-partial-output
  • Interactive Features: Context selection with @, slash commands, and keyboard shortcuts
  • Cross-Platform Support: Complete instructions for macOS (including Homebrew), Linux/Ubuntu, and Windows WSL

Contents

  • SKILL.md: The core skill definition file containing all commands, workflows, and usage instructions
  • README.md: This file, providing an overview and quick reference

Quick Start

Install the Cursor CLI:

# Standard installation (macOS, Linux, WSL)
curl https://cursor.com/install -fsS | bash

# Homebrew (macOS only)
brew install --cask cursor-cli

Authenticate:

agent login

Start an interactive session:

agent

Switch models:

agent models

Usage

Refer to SKILL.md for comprehensive instructions on:

  • Installation and authentication
  • Interactive and non-interactive modes
  • Model switching and configuration
  • MCP server management
  • Rules and commands creation
  • Slash commands and keyboard shortcuts
  • Workflows for code review, refactoring, debugging, and CI/CD integration

Security Audit

Low

Summary

A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).

Risk Profile Toxicity Privacy Scope Reputation Quality

ToxicSkills Analysis

Blocklist
Not matched
Prompt Injection
Not detected

No Toxic signals detected by current static checks.

Key Risks 0 items

No LLM risk bullets (LLM disabled or not cached).

Deterministic Findings (Evidence)

Rule Severity File Snippet
QUALITY_README_PRESENT low README Line n/a
README detected

Scoring Criteria

Each skill is scored across 5 dimensions. The weighted total determines the star rating.

Code Toxicity 100/100 (weight 30%)
Privacy Risk 100/100 (weight 25%)
Permission Scope 100/100 (weight 20%)
Author Reputation 75/100 (weight 15%)
Code Quality 78/100 (weight 10%)

Star Rating Scale

5★ Safe — Score ≥ 80
4★ Good — Score 70–79
3★ Caution — Score 60–69
2★ Risky — Score 40–59
1★ Dangerous — Score < 40

Why This Score?

All dimensions scored above 60. This skill passed the safety baseline.

Explore More Skills

VettedSkillsHub

We curate the top 100 most downloaded skills from ClawHub — the official ClawdBot (OpenClaw) marketplace — then run independent 5-dimension security audits. Transparent evidence, reproducible scores, 1-click install.

About

Best-effort static analysis. Scores are reproducible and evidence-based. Always review code and run in isolated environments for sensitive use.

© 2026 VettedSkillsHub. ClawdBot & OpenClaw are community projects.