spawnterminal

Consiliency's avatarfrom Consiliency

Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.

⭐1stars🔀0forks📁View on GitHub🕐Updated Jan 4, 2026
[Developer Tools]

When & Why to Use This Skill

This Claude skill enables the seamless spawning of new terminal windows to execute a wide range of CLI commands, including ffmpeg, curl, python, and npm. Designed for non-AI command execution, it enhances developer productivity by providing a controlled environment for running scripts and system utilities with built-in safety protocols, such as mandatory syntax verification and optional output logging.

Use Cases

  • Media Processing: Automating video and audio manipulation tasks by executing ffmpeg commands directly in a new terminal.
  • Network & API Testing: Running curl or wget commands to test endpoints, fetch headers, or download resources without leaving the agent environment.
  • Development Workflow: Executing build scripts, package managers (npm/yarn), or version control commands to manage project lifecycles.
  • Environment Scripting: Running Python or Shell scripts for data processing, file management, or local system automation.
namespawn:terminal
description"Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution."

Purpose

Spawn a new terminal window to execute CLI commands. This skill is for generic command execution, NOT for spawning AI agents. For AI agents, use the spawn:agent skill instead.

Variables

Variable Default Description
LOG_TO_FILE false Write full terminal output to debug file
CAPTURE false Block and return output directly

Instructions

MANDATORY - You MUST follow the Workflow steps below in order. Do not skip steps.

  1. Identify the CLI command the user wants to run
  2. Run <command> --help first to verify syntax and options
  3. Execute the command in a new terminal using fork_terminal()

Red Flags - STOP and follow Cookbook

If you're about to:

  • Execute a command without checking its --help first
  • Assume you know the command syntax
  • Skip the --help step "because it's simple"
  • Spawn an AI agent (use spawn:agent instead)

STOP -> Run <command> --help first -> Review output -> Then proceed

Workflow

MANDATORY CHECKPOINTS - Verify each before proceeding:

  1. Understand the user's request
  2. VERIFY: This is a CLI command, NOT an AI agent request
  3. READ: '../agent/fork_terminal.py' to understand the tooling
  4. Follow the Cookbook: Read './cookbook/cli-command.md'
  5. CHECKPOINT: Ran <command> --help and reviewed options
  6. Execute fork_terminal(command, log_to_file=False, log_agent_output=False)

Cookbook

CLI Commands

  • IF: User requests any non-AI CLI command (ffmpeg, curl, python, npm, etc.)
  • THEN: Read and execute './cookbook/cli-command.md'
  • Examples:
    • "Create a new terminal to run ffmpeg"
    • "Spawn terminal with curl"
    • "Fork a terminal to run python script.py"
    • "New terminal: npm run build"

Usage

The fork_terminal() function is located at ../agent/fork_terminal.py:

from spawn.agent.fork_terminal import fork_terminal

# Simple command execution (no output capture)
fork_terminal("npm run build")

# With debug output capture
file_path = fork_terminal("ffmpeg -i video.mp4 output.gif", log_to_file=True)

# Blocking capture (waits for completion)
output = fork_terminal("python script.py", capture=True, log_to_file=True)

When to Use spawn:agent Instead

If the user mentions any of these, use spawn:agent:

  • Claude, Claude Code
  • Codex, OpenAI
  • Gemini, Google
  • Cursor
  • OpenCode
  • Copilot, GitHub Copilot
  • "AI agent", "coding agent", "spawn agent"