Cmux Cloud Vm

OrganizationPopular

manaflow-ai

cmux-cloud-vm

Operate cmux Cloud machines, run durable remote commands or agents, and present their workspaces or services. Use for cmux vm/cloud tasks; backend implementation belongs to cmux-backend.

Overview

Publisher	manaflow-ai
Repository	`cmux`
Skill name	`cmux-cloud-vm`
Stars	27.5K
Forks	2.4K
Bundled files	5
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by manaflow-ai on GitHub. Read the source before you install it.

Installation

Install the Cmux Cloud Vm AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/manaflow-ai/cmux/tree/main/skills/cmux-cloud-vm
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/manaflow-ai/cmux.git /tmp/cmux
mkdir -p .claude/skills
cp -r /tmp/cmux/skills/cmux-cloud-vm .claude/skills/cmux-cloud-vm

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cmux Cloud Vm in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cmux Cloud Vm on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cmux Cloud Vm is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

cmux Cloud machines

Use an existing machine and a workspace for the task. Machine terminals persist when panes close or the Mac disconnects. Work headlessly; open a pane or share a URL when there is a result for the user to inspect.

Start with discovery

sh
cmux vm --help
cmux auth status
cmux vm ls --json
cmux vm route --json

On the Mac, host operations need the app, sign-in and its private tunnel. Inside a machine, use cmux self --json and the guest's help; read guest operations for its supported subset and auth. Installed help is authoritative when versions differ.

route inspects placement without creating a machine. Read would_provision and the backend's limits/capabilities; do not assume a plan cap, memory size or provider feature. Reuse the router's pool machine, or explicitly pin an existing target with --machine <id>. Base is the user's persistent work. Prefer another workspace on a machine to another machine.

Run and observe

After identifying an authorized target, choose the operation:

Need	Start here
Bounded command and exit code	`cmux vm run --machine <id> -- <command>`
Detached coding agent	`cmux vm agent --machine <id> --agent codex --no-open -- "<task>"`
Project with a dev layout	`cmux vm dev <id> --dry-run --json`, then the approved plan
Observe without opening panes	`cmux vm tree <id> --json`, `cmux vm terminal read <id> <term>`
Completion and full output	`cmux vm terminal wait-exit <id> <term>`, then `terminal output`

Read the selected verb's --help before adding flags. Retain the machine, workspace/terminal identity and actual exit result. A finished wait is not proof that tests passed. Use vm open/workspace open to present verified results; closing a view does not stop the machine terminal.

Constraints that apply throughout

Provisioning, forking, resetting, resizing and destructive cleanup need the user's authorization for the target and effect; retain authorization already given. Do not delete machines to make capacity or reset Base as a workaround.
Keep account/upstream tokens on the host. Do not copy the user's credentials into a machine unless requested. Use the secret/env transfer paths when authorized; values do not belong in layout JSON, logs or command arguments.
Use --no-open, --detach or --print while working. Focus changes are intentional. workspace rm kills its terminals; workspace close detaches them.

Read only the relevant detail

Workflow recipes: project setup, interactive terminals, long runs, peer agents, forks and service publication.
Command reference: exact flags, JSON/exit contracts, file/env transfer, layouts, limits and capabilities. Search its task index first.
Guest operations: host/guest grammar, CodeRouter, peer access, mirror behavior, notifications and browser authentication.
Sidebar parity: map a specific UI action to CLI.
Local workspace rules: presenting cloud work without disrupting the caller's workspace.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cmux Cloud Vm AI skill do?

Operate cmux Cloud machines, run durable remote commands or agents, and present their workspaces or services. Use for cmux vm/cloud tasks; backend implementation belongs to cmux-backend.

Why use Cmux Cloud Vm on TypingMind?

Because you install it once and use it with any model. Cmux Cloud Vm is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cmux Cloud Vm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/manaflow-ai/cmux/tree/main/skills/cmux-cloud-vm. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cmux Cloud Vm?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cmux Cloud Vm?

As many as you like. As long as a model supports skills, you can use Cmux Cloud Vm with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cmux Cloud Vm AI skill free?

It is published on GitHub by manaflow-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Algorithmic Art

anthropics

OrganizationPopular

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or…

Doc Coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

Authoring Skills

How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs…

Dce Edge

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render /…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

cmux Cloud machines

Start with discovery

Run and observe

Constraints that apply throughout

Read only the relevant detail

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now