Terminal Opener

SkillDev tools

terminal-opener is a skill that lets an AI agent open an executable and its argument array in a visible terminal window on your computer. It builds a reusable, shell-free launch plan so the command runs as separate process entries rather than a shell string. You can inspect a dry-run JSON plan before anything opens, and it can detect whether a supported terminal exists.

Use Terminal Opener in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Terminal Opener and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Terminal Opener skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Make sure the executable you want to launch and its arguments are known.

Terminal OpenerStart free

What your AI can do with it

  • Open an executable with its argument array in a visible terminal window
  • Show a dry-run JSON plan of the exact launch before opening anything
  • Detect whether a supported terminal exists on the machine
  • Use a detached fallback when no supported terminal is available
  • Run a standalone recovery mode that skips user terminal configuration

Getting started

  1. Make sure the executable you want to launch and its arguments are known.
  2. Add the skill to your agent so it can build a launch plan.
  3. Ask the agent for a dry-run JSON plan and review the executable and arguments.
  4. Confirm the plan so the agent opens the command in a visible terminal window.
  5. If no supported terminal is detected, let the skill use its fallback or recovery mode.

What this skill tells your AI

The instructions your AI receives, as published by affaan-m/ecc in skills/terminal-opener/SKILL.md and read by ahel’s review.

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:

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:

--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.

Signals

GitHub stars
270k
Forks
40k
Last commit
Sep 2026

Questions

Does it open the command through a shell?
No. It keeps the command as separate process entries instead of a shell string, so the executable and its argument array are launched directly.
Can I see what will be launched before it opens?
Yes. The skill can produce a dry-run JSON plan showing the exact launch, so you can inspect the executable and arguments before anything opens.
What happens if no supported terminal is found?
The skill detects whether a supported terminal exists and can use a detached fallback or a standalone recovery mode that skips user terminal configuration.
Advanced
Item type
skill
Key
terminal-opener
Source
github.com/affaan-m/ecc