Claude Auto Launcher — AI skill for Claude Code
Windows launcher for Claude Code: account picker, remembered model and effort, session picker, maintenance screen.
How to install Claude Auto Launcher
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open vitaliy-shatskiy/claude-auto-launcher and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Auto Launcher does
Windows launcher for Claude Code: account picker, remembered model and effort, session picker, maintenance screen.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Open Science — Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux 1.5k ★
- Codex Skill — by klaudworks - Enables users to prompt codex from claude code 914 ★
README
claude-auto-launcher
[](https://github.com/vitaliy-shatskiy/claude-auto-launcher/actions/workflows/ci.yml) [](LICENSE)
A Windows PowerShell launcher for Claude Code: an account picker, remembered model/effort/advisor/ permission choices per account, a project picker, a session-resume picker, and a maintenance screen, all driven by one config file so nothing here is hardcoded to a particular machine.
Unofficial and unaffiliated with Anthropic. It runs the `claude` CLI you already have; bugs in the CLI itself belong [upstream](https://github.com/anthropics/claude-code/issues).
╭────────────────────────────────────────────────────────────────────────────╮
│ ✻ claude-auto │
╰────────────────────────────────────────────────────────────────────────────╯
❯ account [work]
model ‹ Sonnet 5 ›
effort ○ low ○ medium ● [high] ○ xhigh ○ max ○ ultracode
advisor ● [default] ○ fable ○ opus ○ off
permission ○ plan ● [auto] ○ acceptEdits ○ bypass
mode ● [normal] ○ safe
──────────────────────────────────────────────────────────────────────────
w/s row ┊ a/d value ┊ enter next ┊ u maintenance ┊ esc quit
The bracketed values above are what `default` resolves to in the reader's own `settings.json` (`model`, `effortLevel`, `advisorModel`, `permissions.defaultMode`) and differ per machine; a key that file does not set reads `default`, as the advisor row does here. The model names come out of the installed `claude.exe` itself, so they follow the CLI's releases.
Requirements
- PowerShell 7 (
pwsh) - required, not preferred. Typed in a Windows PowerShell 5.1 window the launcher re-execs itself underpwsh; with nopwshon the machine at all it refuses and says so. It used to carry on
Related Skills
ClaudeCode Launchpad CLI
9 Windows & macOS 2-minute installer for Claude Code — auto-installs Node.js, Git & Claude Code; two-line live
Hachibu
Claude Code's model, effort, and usage limits in a small strip that stays on top of your Mac's screen. Unoffic
Polyagent MCP
Let any AI agent (Claude Code, Codex, Gemini/Antigravity) delegate to the Cursor CLI agent via MCP: cheap/fast
Claude Toolkit
Small, honest Claude Code tools for the CLI and desktop app. /handoff mirrors your current session into a fres
Cursor MCP Bridge
Let any AI agent (Claude Code, Codex, Gemini/Antigravity) delegate to the Cursor CLI agent via MCP: cheap/fast
Claude MCP Bridge
Let any AI agent (Cursor, Codex, Gemini/Antigravity) delegate to Claude Code via MCP: adversarial code review,
Related Agents
Fable High
Generic worker pinned to model Fable 5.1 at effort high. Use only when explicitly dispatching per the superpow
Effort High
Pins HIGH reasoning effort; pair with a per-call model param. Guarantees careful multi-step reasoning even whe
Ocx Self
Self-clone: delegate to your default main model (opus[1m]), synced from the /model picker at launch. NOTE: thi