Skip to main content
Agent skill

Terminal Opener

Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery modes. Use when Codex needs to open an interactive CLI, SSH session, local development process, sandbox, or other argv-based command in a new host terminal; diagnose whether a supported terminal is available; or provide an actionable plan when the requested terminal is unsupported.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Terminal Opener when an AI agent needs a reusable SKILL.md workflow for this job: Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery modes. Use when Codex needs to open an interactive CLI, SSH session, local development process, sandbox, or other argv-based command in a new host terminal; diagnose whether a supported terminal is available; or provide an actionable plan when the requested terminal is unsupported.

When not to use it

Skip Terminal Opener when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/terminal-opener
# Save SKILL.md to ~/.claude/skills/terminal-opener/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/terminal-opener/SKILL.md. For a shared project, commit the folder at .claude/skills/terminal-opener/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Terminal Opener skill for this task: Use Terminal Opener when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

71/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
63/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Terminal Opener

Use `scripts/open-terminal.js` to preserve an executable and every argument as separate process entries. Never interpolate a shell command string. Keep every spawn on `shell: false`. Default to a non-launching plan. Use `--launch` only after the user explicitly requests a real window and the argv has been reviewed. The launched process inherits the full environment of the calling process, including secret-bearing variables. The launcher does not filter the environment. Run it from a shell whose environment is safe to expose to the target command.

## Launch a command

Pass launcher options before `--`, then pass exactly one executable followed by its argument array:

```bash node skills/terminal-opener/scripts/open-terminal.js \ --launch \ --cwd /absolute/host/path \ -- ssh -t example.test command-with-arguments ```

Run normal mode first. Let WezTerm try its mux with a new window, then let the launcher fall back to a detached `wezterm start` process if the mux is not available. When fallback is used, read `muxFailure` from JSON output (or the human-readable failure line) to diagnose why the mux path failed.

## Recover from terminal configuration

Add `--recover` or `--standalone` when user configuration or mux state may interfere with the requested command. Start a detached WezTerm process with:

```text --skip-config start --always-new-process ```

Expect recovery mode to skip all user terminal configuration intentionally.

## Inspect before launch

Omit `--launch` (or add `--dry-run`) and add `--json` to inspect the exact executable, argv, working directory, terminal adapter, primary launch, and fallback without opening a window. Treat the JSON plan as the composition boundary for callers.

Run `--detect --json` without a command to probe terminal availability. Follow the returned `action` when the adapter is missing or unsupported. Use WezTerm for the current adapter; treat other requested terminals as unsupported plans, not as commands to execute.

Intended uses

  • Use Terminal Opener when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.