cursor-agentA comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Install via ClawdBot CLI:
clawdbot install swiftlysingh/cursor-agentThis skill provides a comprehensive guide and set of workflows for utilizing the Cursor CLI tool, including all features from the January 2026 update.
curl https://cursor.com/install -fsS | bashbrew install --cask cursor-climacOS:
~/.zshrc (zsh) or ~/.bashrc (bash):
export PATH="$HOME/.local/bin:$PATH"source ~/.zshrc (or ~/.bashrc)Linux/Ubuntu:
agent --versionBoth platforms:
agent (primary) and cursor-agent (backward compatible)agent --version or cursor-agent --versionAuthenticate via browser:
agent loginOr use API key:
export CURSOR_API_KEY=your_api_key_hereKeep your CLI up to date:
agent update
# or
agent upgradeStart an interactive session with the agent:
agentStart with an initial prompt:
agent "Add error handling to this API"Backward compatibility: cursor-agent still works but agent is now the primary command.
List all available models:
agent models
# or
agent --list-modelsUse a specific model:
agent --model gpt-5Switch models during a session:
/modelsManage your agent sessions:
agent lsagent resumeagent --resume="[chat-id]"Include specific files or folders in the conversation:
@filename.ts
@src/components/Available during interactive sessions:
/models - Switch between AI models interactively/compress - Summarize conversation and free up context window/rules - Create and edit rules directly from CLI/commands - Create and modify custom commands/mcp enable [server-name] - Enable an MCP server/mcp disable [server-name] - Disable an MCP serverShift+Enter - Add newlines for multi-line promptsCtrl+D - Exit CLI (requires double-press for safety)Ctrl+R - Review changes (press i for instructions, navigate with arrow keys)ArrowUp - Cycle through previous messagesRun the agent in a non-interactive mode, suitable for CI/CD pipelines:
agent -p 'Run tests and report coverage'
# or
agent --print 'Refactor this file to use async/await'Output formats:
# Plain text (default)
agent -p 'Analyze code' --output-format text
# Structured JSON
agent -p 'Find bugs' --output-format json
# Real-time streaming JSON
agent -p 'Run tests' --output-format stream-json --stream-partial-outputForce mode (auto-apply changes without confirmation):
agent -p 'Fix all linting errors' --forceMedia support:
agent -p 'Analyze this screenshot: screenshot.png'CRITICAL: When running Cursor CLI from automated environments (AI agents, scripts, subprocess calls), the CLI requires a real TTY. Direct execution will hang indefinitely.
The Solution: Use tmux
# 1. Install tmux if not available
sudo apt install tmux # Ubuntu/Debian
brew install tmux # macOS
# 2. Create a tmux session
tmux kill-session -t cursor 2>/dev/null || true
tmux new-session -d -s cursor
# 3. Navigate to project
tmux send-keys -t cursor "cd /path/to/project" Enter
sleep 1
# 4. Run Cursor agent
tmux send-keys -t cursor "agent 'Your task here'" Enter
# 5. Handle workspace trust prompt (first run)
sleep 3
tmux send-keys -t cursor "a" # Trust workspace
# 6. Wait for completion
sleep 60 # Adjust based on task complexity
# 7. Capture output
tmux capture-pane -t cursor -p -S -100
# 8. Verify results
ls -la /path/to/project/Why this works:
agent calls from subprocess/exec hang without TTYWhat does NOT work:
# ❌ These will hang indefinitely:
agent "task" # No TTY
agent -p "task" # No TTY
subprocess.run(["agent", ...]) # No TTY
script -c "agent ..." /dev/null # May crash CursorThe agent automatically loads rules from:
.cursor/rulesAGENTS.mdCLAUDE.mdUse /rules command to create and edit rules directly from the CLI.
MCP servers are automatically loaded from mcp.json configuration.
Enable/disable servers on the fly:
/mcp enable server-name
/mcp disable server-nameNote: Server names with spaces are fully supported.
Perform a code review on the current changes or a specific branch:
agent -p 'Review the changes in the current branch against main. Focus on security and performance.'Refactor code for better readability or performance:
agent -p 'Refactor src/utils.ts to reduce complexity and improve type safety.'Analyze logs or error messages to find the root cause:
agent -p 'Analyze the following error log and suggest a fix: [paste log here]'Automate git operations with context awareness:
agent -p 'Generate a commit message for the staged changes adhering to conventional commits.'Run automated checks in CI pipelines:
# Set API key in CI environment
export CURSOR_API_KEY=$CURSOR_API_KEY
# Run security audit with JSON output
agent -p 'Audit this codebase for security vulnerabilities' --output-format json --force
# Generate test coverage report
agent -p 'Run tests and generate coverage report' --output-format textUse context selection to analyze multiple files:
agent
# Then in interactive mode:
@src/api/
@src/models/
Review the API implementation for consistency with our data modelsGenerated Mar 1, 2026
Integrate the Cursor CLI agent into a continuous integration pipeline to automatically review pull requests for security vulnerabilities, performance issues, and code quality. The agent can analyze code changes, run tests, and generate structured JSON reports that can be parsed by other tools to block or flag problematic commits.
Use the agent in non-interactive mode with the --force flag to automatically refactor large, outdated codebases in financial or healthcare systems. It can modernize code by converting callbacks to async/await, improving type safety, and reducing complexity without manual intervention, saving developer time on tedious updates.
Deploy the agent in a production monitoring setup to analyze error logs and system outputs in real-time. By piping logs to the agent with specific prompts, it can identify root causes of failures, suggest fixes, and even generate patches, reducing mean time to resolution for critical incidents.
Incorporate the agent into coding bootcamps or online learning platforms to provide instant feedback on student assignments. Using interactive sessions, students can get explanations, debug help, and code improvements, while instructors can use non-interactive mode to batch-grade projects efficiently.
Leverage the agent to automate the creation and updating of technical documentation, API references, and internal wikis. By analyzing codebases and using prompts, it can generate clear, structured documentation, ensuring consistency and reducing manual writing efforts for engineering teams.
Offer a cloud-based service where teams subscribe to use the Cursor CLI agent integrated with their development environments. Revenue comes from monthly or annual subscriptions based on usage tiers, number of users, and advanced features like priority support or custom model access.
Sell enterprise licenses to large corporations in industries like finance or healthcare, providing on-premise deployment, enhanced security, and custom integrations. This includes dedicated support, training, and compliance features, with pricing based on the number of developers or projects.
Provide a free tier of the Cursor CLI agent for individual developers or small teams, with limited usage or basic features. Monetize through premium add-ons such as advanced AI models, increased API limits, team collaboration tools, and automation capabilities like the tmux integration for CI/CD.
💬 Integration Tip
For automation, always use tmux to provide a TTY when running the agent from scripts or AI environments, as direct subprocess calls will hang without it.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks