Claude Code Launcher

Launch Claude Code in a new terminal window with Remote Control enabled. Use when opening a project for interactive coding sessions where you need to access...

Security Scan

The skill's files, script, and runtime instructions match its stated purpose (launching Claude Code and enabling Remote Control); nothing requested or installed is disproportionate, but it does capture screenshots and logs and starts a tool that can expose project contents to the Claude service, so treat it as privacy-sensitive.

Purpose & Capability

Name/description, SKILL.md, and the included launch_claude_code.sh script are coherent: the script automates opening Terminal, cd'ing to a project, running `claude code`, sending `/remote-control`, and capturing a screenshot and logs. Required tools (peekaboo, claude CLI) are consistent with the stated functionality.

Instruction Scope

Instructions stay within the claimed scope (terminal automation, navigation, starting Claude Code, enabling Remote Control, screenshot capture, logging). Important privacy/security behavior is explicit: it captures screenshots, writes logs to ~/.openclaw/workspace/logs/claude-code-launcher, and makes the project available to the running Claude Code process — which can expose code or secrets to the remote Claude service. This is expected for the feature but is sensitive and worth user attention.

Install Mechanism

No install spec is provided (instruction-only skill) and the script references standard third-party CLIs (peekaboo via Homebrew tap and claude CLI via npm/Homebrew). No remote archive downloads or obscure URLs are used by the skill itself.

Credentials

The skill requests no environment variables or credentials. It requires local permissions (Accessibility / Screen Recording) and write access to the target project and to ~/.openclaw workspace for logs. Those permissions and file accesses are proportionate to the automation task but can expose sensitive data (screenshots, session URLs, project files) so users should grant them only if they trust the workflow and the remote Claude service.

Persistence & Privilege

always is false and there is no installer that modifies other skills. The script creates logs under the user's home but does not request persistent elevated privileges or make system-wide configuration changes. Normal agent autonomy applies but is not exceptional here.

Assessment

This skill appears to do what it says, but it performs sensitive local actions: it opens Terminal, runs `claude code` in your project directory (giving that process access to your project files), types UI commands via peekaboo, captures screenshots, and writes logs (including potential session URLs) to ~/.openclaw/workspace/logs/claude-code-launcher. Before installing/use: 1) Inspect the included script yourself (it is readable and matches the doc). 2) Verify you trust the Claude service and the claude CLI installation source. 3) Confirm you are comfortable granting Accessibility and Screen Recording permissions (these enable the automation and screenshots). 4) Run the script on a non-sensitive project first to observe behavior. 5) If you want to reduce risk, run the steps manually instead of granting automation, or remove screenshot/logging lines from the script. 6) Periodically review and delete logs that might contain session URLs or other secrets.

Overview

This skill automates the process of launching Claude Code in a new terminal window with Remote Control enabled. It streamlines the workflow of:

1. Opening a fresh terminal window
2. Navigating to a project directory
3. Starting Claude Code
4. Activating Remote Control mode
5. Handling user confirmations (if needed)
6. Capturing and displaying the final state

Perfect for switching between projects quickly or sharing Claude Code sessions across devices.

Usage

Basic Launch

claude-code-launcher /path/to/project

With Options

claude-code-launcher /path/to/project --verbose --screenshot

From OpenClaw Chat

Simply ask:

• "Launch Claude Code in proposal-generator with Remote Control"
• "Open the ai-native-lms project and enable Remote Control"
• "Start Claude Code in ~/dev/edikar-standalone"

How It Works

Step 1: Terminal Preparation

• Opens a new Terminal window using macOS automation
• Ensures fresh shell environment (zsh)
• Waits for the window to be ready

Step 2: Project Navigation

• Changes directory to the specified project path
• Validates that the directory exists
• Reports any path resolution errors

Step 3: Claude Code Launch

• Executes claude code command
• Waits for Claude Code interface to fully load (~5 seconds)
• Monitors for startup errors (missing dependencies, permission issues)

Step 4: Remote Control Activation

• Types /remote-control command into Claude Code
• Presses Enter to submit
• Waits for Remote Control UI to appear (~3-6 seconds)

Step 5: User Confirmation

• Detects the "Continue" option in Remote Control menu
• Presses Enter to confirm (or prompts user if needed)
• Validates that Remote Control is now active

Step 6: Session Capture

• Takes a screenshot of the final state
• Displays the Remote Control session URL
• Extracts and displays QR code information
• Reports success or any errors encountered

Error Handling

The skill handles these common scenarios:

Issue	Recovery
Terminal fails to open	Retries once, then reports error
Project path doesn't exist	Displays helpful path resolution suggestions
Claude Code not installed	Reports missing dependency and suggests brew install claude
Claude Code hangs	Timeout after 15 seconds, allows manual intervention
Remote Control fails to activate	Logs error details, suggests checking Claude version
Terminal permissions denied	Requests user to enable Screen Recording in System Preferences
Network connectivity issue	Waits up to 10 seconds for reconnection

Resources

scripts/launch_claude_code.sh

Main automation script using Peekaboo CLI for:

• Terminal window management
• Keyboard/text input automation
• Screenshot capture
• Error detection and recovery
• Logging all operations to ~/.openclaw/workspace/logs/claude-code-launcher.log

references/troubleshooting.md

Common issues and solutions:

• Permission setup (Screen Recording, Accessibility)
• Claude Code installation and updates
• Terminal app configuration
• Network troubleshooting

Prerequisites

✅ Installed: peekaboo (for UI automation)
✅ Installed: claude CLI (Claude Code)
✅ System: macOS with Terminal.app
✅ Permissions: Screen Recording + Accessibility enabled

To enable permissions:

System Settings → Privacy & Security → Screen Recording → Enable OpenClaw
System Settings → Privacy & Security → Accessibility → Enable OpenClaw

What You Get

After launching, you'll have:

• ✅ New Terminal window with Claude Code running
• ✅ Remote Control session active and shareable
• ✅ Session URL for accessing from other devices
• ✅ QR code for mobile devices (scan in Claude app)
• ✅ Full context of your project available to Claude
• ✅ Capability to pause/resume across devices

Example Workflow

User: "Launch Claude Code in edikar-standalone with Remote Control"
↓
Skill opens new Terminal
↓
cd ~/dev/edikar-standalone
↓
claude code
↓
/remote-control
↓
[Confirms continuation]
↓
Screenshot captured
↓
User sees:
   - Session URL: https://claude.ai/code/session_...
   - QR code displayed
   - Ready to access from phone/tablet

Related Commands

• /remote-control - Activate Remote Control in Claude Code
• claude code - Start Claude Code interactive session
• peekaboo - macOS UI automation (used internally)

---

Need help? See references/troubleshooting.md for common issues and solutions.