Configure the Multi launch command and model selection for installed providers.

Apache-2.0Auto-check: notes

Install Setup

skills CLI
$ npx skills add greenpolo/cc-multi-cli-plugin --skill setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install greenpolo/cc-multi-cli-plugin setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/greenpolo/cc-multi-cli-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/multi-core/skills/setup .claude/skills/setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
setup
GitHub stars
187
Token cost
~750 tokens
SKILL.md length
381 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Configure the Multi launch command and model selection for installed providers.

  • Tasks that involve Model routing and gateways
  • Calls node and claude

What it does

Setup is an agent skill from greenpolo/cc-multi-cli-plugin. Configure the Multi launch command and model selection for installed providers.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with OpenAI and PowerShell. The repository describes itself as: Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, delegate to named native workers, keep… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Model routing and gateways

Example prompts

  • “/setup”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Bash

What it can do on your machine

Read from SKILL.md and the folder at commit 3dcb057. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node
    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setup loads about 750 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 381 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~750

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from greenpolo/cc-multi-cli-plugin at commit 3dcb057, republished under its Apache-2.0 licence (© greenpolo). 381 words, ~750 tokens.

Download SKILL.mdSave it as .claude/skills/setup/SKILL.md (or your agent's skills folder).
name
setup
description
Configure the Multi launch command and model selection for installed providers.
allowed-tools
Bash
disable-model-invocation
true

Check node --version (requires >=24.12) and claude --version. Use a persistent Node installation: setup records its executable path, so a temporary npx download will break startup when removed. This user-invoked setup installs small wrappers and adds one marked PATH block to ~/.bashrc, ~/.zshrc, fish's config file, or the PowerShell profile. It preserves the real Claude executable and existing settings. Explain these changes, then offer two optional customizations before running setup. Use the defaults unless the user chooses otherwise:

  • Launch command name (default claude-multi). The wrapper starts Claude Code with Multi's gateway, model, worker, and hook configuration. Choose a name such as multiclaude; multi is reserved. Pass it with --command <name>. Naming it claude shadows the plain command for every launch, including scripts, editors and agents that run claude; explain that before accepting it.
  • Models shown in /model (default: curated rows for connected providers). Pass --models <id,id,...> with full IDs such as multi/openai/gpt-6-astra from the provider docs, --models none to hide external rows, or --models all to show the full connected catalog. Claude's own models always stay listed. Use --models +<id,id,...> to add models to the saved selection; with no saved selection, it extends the curated defaults. Existing explicit selections remain until changed. If a requested worker is unavailable, find its model ID in the provider docs or with --cursor-models / --zen-models, add it to the displayed models, and relaunch the session.
Show full SKILL.md (151 more words)Show less

Run the helper using this plugin's root, adding the chosen flags. Choose the syntax for the target shell.

Linux/macOS (POSIX shell):

sh
node "${CLAUDE_PLUGIN_ROOT}/plugins/multi-core/src/setup.ts"

Windows PowerShell:

powershell
node "$env:CLAUDE_PLUGIN_ROOT/plugins/multi-core/src/setup.ts"

Windows cmd:

bat
node "%CLAUDE_PLUGIN_ROOT%\plugins\multi-core\src\setup.ts"

Re-running setup without flags keeps the previous command name and model selection.

If the user's shell cannot be identified, ask whether they use Bash, Zsh, fish, PowerShell, or cmd, then pass the matching --shell value. Never pass an API key as an argument. Keep provider login separate from setup. Report failures without claiming completion. On success, tell the user to open a new terminal, run multi status, and start the launch command (claude-multi by default) to launch Multi. Unless the user chose the name claude, setup never replaces or shadows the claude command; plain claude keeps starting ordinary Claude Code unchanged. Existing sessions do not acquire a new gateway. Install provider plugins at user scope with the normal plugin installer; do not manually edit Claude caches.

© greenpolo, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/multi-core/skills/setup of greenpolo/cc-multi-cli-plugin.

Open the folder on GitHubat commit 3dcb057

Compare with similar skills

Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setup this skillgreenpolo/cc-multi-cli-plugin187—~750Automated safety check: NotesApache-2.0
9Router AI Gateway Setupdecolua/9router30k—~744Automated safety check: PassMIT
9Router Chat Completionsdecolua/9router30k—~635Automated safety check: PassMIT
Agent Squad Python Guide2FastLabs/agent-squad7.8k—~4.7kAutomated safety check: PassApache-2.0
Embeddings via 9Routerdecolua/9router30k—~604Automated safety check: PassMIT
Survey Generatorrohitg00/pro-workflow2.9k1 repos~1.6kAutomated safety check: PassNone

Similar skills

  • Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.

    30k GitHub stars~744 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed
  • Sends chat and code-generation requests through a 9Router gateway using OpenAI or Anthropic message formats, with streaming and auto-fallback combos.

    30k GitHub stars~635 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed
  • Agent Squad Python Guide

    2FastLabs/agent-squad

    Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.

    7.8k GitHub stars~4.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    30k GitHub stars~604 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed
  • Survey Generator

    rohitg00/pro-workflow

    Compile a structured literature survey on any AI/ML topic. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~1.6k tokens
    Research & ScienceAuto-check passed
  • Local test harness for the Weave router: a docker compose stack plus codex exec runs that confirm how Codex requests are routed, translated and marked.

    5.6k GitHub stars~4.7k tokensUpdated today
    Testing & QAAuto-check: notes

More from greenpolo/cc-multi-cli-plugin

All 8 skills in this repo
  • Connect

    greenpolo/cc-multi-cli-plugin

    Install the scoped Antigravity permission hook. An agent skill from greenpolo/cc-multi-cli-plugin.

    187 GitHub stars~208 tokensUpdated 3 days ago
    Auto-check: notes
  • Connect

    greenpolo/cc-multi-cli-plugin

    Save an OpenCode Zen API key without exposing it in chat. An agent skill from greenpolo/cc-multi-cli-plugin.

    187 GitHub stars~202 tokensUpdated 3 days ago
    Auto-check: notes
  • Login

    greenpolo/cc-multi-cli-plugin

    Start the official Cursor SDK login flow. An agent skill from greenpolo/cc-multi-cli-plugin.

    187 GitHub stars~189 tokensUpdated 3 days ago
    Auto-check: notes
  • Login

    greenpolo/cc-multi-cli-plugin

    Sign in to Grok Build for the native harness. An agent skill from greenpolo/cc-multi-cli-plugin.

    187 GitHub stars~294 tokensUpdated 3 days ago
    Auto-check: notes
  • Status

    greenpolo/cc-multi-cli-plugin

    Show enabled Multi providers and the local runtime status. An agent skill from greenpolo/cc-multi-cli-plugin.

    187 GitHub stars~193 tokensUpdated 3 days ago
    Auto-check: notes
  • Uninstall

    greenpolo/cc-multi-cli-plugin

    Remove Multi startup files while preserving provider credentials.

    187 GitHub stars~223 tokensUpdated 3 days ago
    Auto-check: notes

Questions about Setup

What does Setup do?

Configure the Multi launch command and model selection for installed providers. Setup is an agent skill from greenpolo/cc-multi-cli-plugin. Configure the Multi launch command and model selection for installed providers.

When should I use Setup?

Setup fits situations like: tasks that involve Model routing and gateways.

How do I install Setup in Claude Code?

Run `npx skills add greenpolo/cc-multi-cli-plugin --skill setup -a claude-code`. Or copy the skill folder (plugins/multi-core/skills/setup in greenpolo/cc-multi-cli-plugin) into .claude/skills/setup in your project. Claude Code loads it when a task matches its description.

How do I install Setup in Codex?

Run `npx skills add greenpolo/cc-multi-cli-plugin --skill setup -a codex`. Or copy the skill folder (plugins/multi-core/skills/setup in greenpolo/cc-multi-cli-plugin) into .agents/skills/setup in your project. Codex loads it when a task matches its description.

Can I use Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greenpolo/cc-multi-cli-plugin --skill setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup, .gemini/skills/setup, .github/skills/setup and .opencode/skills/setup in your project.

What does Setup need to run?

Going by SKILL.md and its folder, Setup needs the command-line tools its instructions call (node and claude). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash.

Does Setup access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Setup safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Setup use?

Setup is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Setup use?

About 750 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Setup?

Skills that share tags, products or a category with Setup: 9Router AI Gateway Setup (decolua/9router, 30k stars), 9Router Chat Completions (decolua/9router, 30k stars), Agent Squad Python Guide (2FastLabs/agent-squad, 7.8k stars) and Embeddings via 9Router (decolua/9router, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setup?

greenpolo (a GitHub user) maintains it in greenpolo/cc-multi-cli-plugin, which has 187 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 5, 2026.

Source: greenpolo/cc-multi-cli-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.