launch

Launch Code OSS builds with isolated profiles and unique debug ports for Playwright automation and dap-cli debugging.

Updated Aug 30, 2026
One-click install
npx skills add https://github.com/Tyrizx/Tyrizx --skill launch-tyrizx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: launch
Source: https://github.com/Tyrizx/Tyrizx/tree/main/.agents/skills/launch
Command: npx skills add https://github.com/Tyrizx/Tyrizx --skill launch-tyrizx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @playwright/cli, and includes scripts (resource) components.

What problem does it solve? Running VS Code from source for UI automation or debugging normally requires manual profile setup, port management, and sign-in handling. This Skill launches Code OSS into a throwaway, pre-authenticated profile with unique debug ports so you can drive the workbench with @playwright/cli and attach a Node debugger via dap-cli in the same session, without port conflicts or profile corruption. ## Core Features & Use Cases - Isolated authenticated launches: Clones an authenticated user-data-dir (slim copy excluding caches and workspace storage) into a temp folder, preserving Copilot/GitHub sign-in on macOS, Linux, and Windows. - Unique debug ports per instance: Allocates free ports for the renderer (CDP), extension host, main process, and agent host, printed as JSON for programmatic pickup. - UI automation helpers: Includes a Playwright script to focus the chat input and a monaco-paste helper that reliably inserts text into Monaco editors where fill/type fail. - Use Case: An agent working on VS Code itself launches an Agents window, attaches @playwright/cli over CDP, pastes a prompt into the chat input, takes screenshots, and simultaneously sets breakpoints in the extension host via dap-cli. ## Quick Start Ask the AI to launch a Code OSS dev build with an isolated authenticated profile and attach Playwright to its CDP port so you can drive the workbench UI.

Frequently Asked Questions about launch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I launch VS Code from source for UI automation with Playwright?▼

Run the launch.sh script (macOS/Linux) or launch.ps1 (Windows) from the skill's scripts directory. It clones an authenticated profile, picks free debug ports, waits for the CDP endpoint, and prints a JSON line with the cdpPort you pass to npx @playwright/cli attach.

How do I type into the VS Code chat input with Playwright?▼

Playwright's fill and type silently fail on Monaco's native-edit-context element. Use the monaco-paste.sh helper, which dispatches a ClipboardEvent paste with a DataTransfer payload into the focused chat input and verifies the rendered view lines.

Can I run multiple Code OSS instances in parallel for automation?▼

Yes. Each launch allocates fresh ports and its own temp user-data-dir, extensions dir, and shared-data dir, so instances do not conflict. Give each driver a unique @playwright/cli session name via -s=NAME to keep daemons isolated.

Why does the launched Code OSS instance ask me to sign in?▼

The source profile lacks a stored GitHub session. On Windows the session lives in the shared-data-dir, so sign in once by running scripts/code.bat with --user-data-dir pointing at the source profile; future launches copy both the profile and shared data.

How do I debug the VS Code extension host while driving the UI?▼

Attach dap-cli to the extHostPort from the launch JSON for the extension host, mainPort for the Electron main process, or agentHostPort for the agent host. You can run dap-cli and @playwright/cli against the same window simultaneously.

What are the prerequisites for using this launch skill?▼

You need a vscode repo checkout with node_modules installed and a full build via npm run compile or npm run watch, an authenticated source profile such as ~/.vscode-oss-dev, Node on PATH, and @playwright/cli available through npx.