Menu
Terminal User Interface (TUI) instructions for OpenCode - how to navigate and use the OpenCode TUI
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | tui |
| description | Terminal User Interface (TUI) instructions for OpenCode - how to navigate and use the OpenCode TUI |
| author | Tim Sonner |
| license | MIT |
| compatibility | opencode |
| metadata | {"audience":"developers","workflow":"interface","language":"markdown"} |
OpenCode provides a rich Terminal User Interface (TUI) for interacting with the AI coding agent. This guide covers the basics of navigating and using the OpenCode TUI.
After installing OpenCode and configuring your LLM provider, you can start the TUI by running:
opencode
This will launch the OpenCode TUI in your terminal.
The OpenCode TUI uses keyboard shortcuts for navigation and commands:
OpenCode operates in two distinct modes:
Use the @ key to fuzzy search for files in your project:
How is authentication handled in @packages/functions/src/api/index.ts
You can drag and drop images into the terminal to include them in your prompts. OpenCode can analyze and reference these images.
/undo: Revert the last changes made by OpenCode/redo: Reapply changes that were undone/share: Create a shareable link to your current conversationSimply type your question and press Enter. OpenCode will analyze your codebase and provide explanations.
Describe what you want to change, and OpenCode will either:
After OpenCode gives a plan or makes changes, you can:
@ notation/share to share useful conversations with teammatesCommands, man-style CLI flags, and Microsoft.WSL.Containers API for building/running Linux containers via wslc on Windows (no Docker Desktop required).
Run the Antigravity (Gemini) CLI agent harness via the agy binary. Includes interactive session control and exit handling.
Use this skill whenever you need to click, type, or navigate inside a browser window (Edge, Chrome, Firefox, etc.) but the computer-use MCP blocks interaction because the browser is granted at tier 'read'. This skill bypasses that restriction by injecting mouse and keyboard input at the Windows API level via PowerShell and user32.dll—the same technique that worked to navigate Edge to code.visualstudio.com. Trigger this skill any time you see the error 'granted at tier read — visible in screenshots only, no clicks or typing', or any time the user asks you to click or type in a browser and the Claude-in-Chrome extension is not connected.
Python SDK for programmatic control of GitHub Copilot CLI via JSON-RPC
Harden Windows Defender privacy settings for authorized pentest engagements. Disables telemetry uploads, sample submission, and cloud reporting to prevent leaking target info, credentials, and tooling to Microsoft. Includes exclusion management and post-engagement re-enablement.
Specification for building Model Context Protocol servers using Python