Rmux logo

Rmux

OrganizationPopular
Helvesec
rmux

Guide for using RMUX with Claude Code, including the tmux-compatible CLI, agent automation waits, the typed SDK, browser web-share, and the rmux claude launcher.

Overview

PublisherHelvesec
Repositoryrmux
Skill namermux
Stars
2.6K
Forks
156
Bundled files
Instructions only
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Helvesec on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/Helvesec/rmux.git /tmp/rmux
mkdir -p .claude/skills
cp -r /tmp/rmux/resources/claude/skills/rmux .claude/skills/rmux
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rmux 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 Rmux 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 Rmux 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.

RMUX

RMUX is a Rust terminal multiplexer with a tmux-compatible CLI, a typed SDK, browser web-share, and a Claude Code launcher. Prefer checking the installed binary instead of assuming a version:

sh
rmux -V
rmux list-commands
rmux list-commands send-keys

If RMUX is missing, suggest installing the published package for the user's platform or cargo install rmux --locked.

This repository ships this source copy at resources/claude/skills/rmux/SKILL.md so the project can package and install it without keeping a hidden .claude directory in the source tree. To use the guidance, run rmux claude install-skill; it installs a user-level copy under ~/.claude/skills/rmux on Linux/macOS or %USERPROFILE%\.claude\skills\rmux on Windows.

Claude Code

Use rmux claude [args...] to run Claude Code inside an RMUX workspace with tmux teammate mode enabled.

sh
rmux claude
rmux claude --dangerously-skip-permissions

RMUX passes --teammate-mode tmux to Claude and scopes a private tmux shim to the Claude process. The shim lets Claude's tmux-compatible teammate commands drive RMUX panes without replacing the user's system tmux. Set RMUX_DISABLE_TMUX_SHIM=1 only when the user explicitly wants to disable that shim.

For reliable Claude Code workflows, prefer rmux claude over starting a plain daemon from inside an arbitrary Claude shell. On Unix, if the user is not using rmux claude and their daemon is killed when Claude recycles a shell, starting the daemon with setsid rmux new-session -d -s NAME can detach it from that shell. setsid is Unix-only; on Windows, use rmux claude.

Agent Automation

Avoid blind sleeps. Send input with a bounded wait and inspect output when needed:

sh
rmux new-session -d -s work
rmux send-keys -t work --wait quiet --stable-for 500ms --timeout 2m -- 'cargo test' Enter
rmux capture-pane -t work -p

Recommended waits:

  • --wait quiet waits for output to settle and is the default choice for builds, tests, and shell commands with unknown final text.
  • --wait-next-text TEXT waits for new output only and avoids matching old scrollback.
  • --wait-visible-text TEXT waits for rendered visible text.
  • --wait-pane-exit is for one-shot pane processes that are expected to exit.
  • Always pair waits with --timeout.

When using send-keys with any --wait* flag, put -- before the payload keys. --wait-text and --wait-next-text observe raw PTY output, including shell echo. If the marker appears in the command itself, prefer --wait quiet or disable shell echo first.

Useful automation commands:

sh
rmux wait-pane -t work --quiet --timeout 30s
rmux stream-pane -t work --lines
rmux collect-pane-output -t work --until-pane-exit --max-bytes 1048576

CLI Basics

RMUX mirrors tmux syntax for common session, window, and pane operations:

sh
rmux new-session -d -s NAME
rmux attach-session -t NAME
rmux list-sessions
rmux split-window -h -t NAME
rmux split-window -v -t NAME
rmux list-panes -t NAME
rmux kill-session -t NAME
rmux kill-server

Use rmux list-commands COMMAND to confirm the exact tmux-compatible flags for the installed version.

Web Share

Use rmux web-share to open an existing pane or session in a browser. Operator links can send input; spectator links are read-only.

sh
rmux web-share
rmux web-share -t work
rmux web-share --spectator-only
rmux web-share --operator-only
rmux web-share --tunnel-provider localhost-run
rmux web-share --no-pin
rmux web-share --ttl 3600
rmux web-share list
rmux web-share stop SHARE_ID

For public read-only demos, prefer --spectator-only and put external per-client throttling at the tunnel, CDN, or reverse proxy layer.

SDK

RMUX exposes typed SDKs. The Rust crate is rmux-sdk; Python is librmux; TypeScript is @rmux/sdk. Prefer the SDK for structured automation instead of parsing terminal text when the task is programmatic.

Rust shape:

rust
use rmux_sdk::{EnsureSession, EnsureSessionPolicy, Rmux, SessionName};

let rmux = Rmux::builder().connect_or_start().await?;
let session = rmux
    .ensure_session(
        EnsureSession::named(SessionName::new("work")?)
            .policy(EnsureSessionPolicy::CreateOrReuse)
            .detached(true),
    )
    .await?;

let pane = session.pane(0, 0);
pane.send_text("printf 'ready\\n'\n").await?;
pane.wait_for_text("ready").await?;
let snapshot = pane.snapshot().await?;
println!("{}", snapshot.visible_text());

Key SDK reminders:

  • send_text sends text; include a trailing newline when the shell should run the command.
  • send_key sends a named key such as Enter or C-c.
  • Prefer daemon-side waits such as wait_for_text_next when available.
  • Killing the last session can shut down the daemon; reconnect before more operations.

Frequently asked questions

What does the Rmux AI skill do?

Guide for using RMUX with Claude Code, including the tmux-compatible CLI, agent automation waits, the typed SDK, browser web-share, and the rmux claude launcher.

Why use Rmux on TypingMind?

Because you install it once and use it with any model. Rmux 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 Rmux in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Helvesec/rmux/tree/main/resources/claude/skills/rmux. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rmux?

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 Rmux?

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

Is the Rmux AI skill free?

It is published on GitHub by Helvesec. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇