Skip to main content
skill CX Codex

openrig-cmux — Claude Code skill: what it does, how to install

Renders OpenRig agent fleets, missions, and pods into live cmux terminal tiles. Helpful when monitoring running agents without disrupting active sessions.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mvschwarz/openrig --skill openrig-cmux -a claude-code
Open on GitHub

What openrig-cmux does

The skill instructs an agent to display OpenRig fleet sessions directly in cmux. Using rig terminal open <view> --provider cmux, it arranges rigs, pods like pod:<rig>/<podNamespace>, missions, slices, or saved views into tiled panes. If a node is already open, cmux brings it into focus instead of launching a duplicate tile.

Session handling mirrors the rules from openrig-herdr. Mission and slice views attach via tmux attach -r in read-only mode, guaranteeing that keystrokes never reach running background agents. If a host is connected over HTTP, the tile degrades with an explicit warning because live streaming demands an SSH link.

Keep in mind that cmux is treated as a best-effort provider, while herdr remains OpenRig's default choice. Custom layouts must be configured by hand in terminal-views.yaml, as there is no built-in write command.

What it helps with

  • render OpenRig rigs and pods into cmux terminal tiles
  • inspect running mission slices in read-only mode
  • check provider health with rig terminal status
  • navigate hand-authored fleet layouts in terminal-views.yaml

Example prompts for the agent

  • Open slice <id> into cmux tiles
  • List available views using rig terminal views
  • Check provider health with rig terminal status --provider cmux

How to install openrig-cmux

1Skills CLI (Vercel)

npx skills add mvschwarz/openrig --skill openrig-cmux -a claude-code

2Manually: put the files in place

~/.claude/skills/openrig-cmux/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openrig-cmux/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openrig-cmux

How to install openrig-cmux in Claude Code?

Run npx skills add mvschwarz/openrig --skill openrig-cmux -a claude-code. The skill file is placed in ~/.claude/skills/openrig-cmux/SKILL.md.

What is the difference between openrig-cmux and openrig-herdr?

herdr is the default proof-gated provider, while cmux acts as a best-effort alternative. Both share the same view semantics and safety rails, but cmux focuses existing tiles rather than duplicating them.

Why does an agent tile enter a degraded state?

Interactive terminal tiles require SSH. When a host is registered only via HTTP, OpenRig reports an honest degradation notice instead of silently failing.

Source text

SKILL.md · Apache-2.0
---
name: openrig-cmux
description: >
  Use when opening OpenRig fleet terminals into cmux — turning a rig, pod, mission, slice, or saved
  view into live agent tiles via `rig terminal --provider cmux`, or driving cmux on an agent's
  request. Same OpenRig view semantics as openrig-herdr (the verbs, honest-partial/degrade, read-only
  cross-rig, scroll/copy, same-size-only duplicates); cmux is the **best-effort** provider (herdr is
  the default and the proof-gated one). Prefer openrig-herdr unless cmux is specifically wanted.
metadata:
  openrig:
    stage: candidate
    sibling_skills:
      - openrig-herdr
      - openrig-user
---

# openrig-cmux

cmux is a **provider** for OpenRig views — the same `rig terminal` surface as herdr, rendering the
tiles into cmux instead. It is the provider OpenRig already shipped (the existing "Launch in cmux"
affordance generalizes onto `rig terminal <provider>`), kept working. The OpenRig-semantic half is
identical to openrig-herdr: OpenRig decides **which** agents form a view; the provider renders the
pixels. **Read openrig-herdr first for the full model** — this skill only calls out what differs for
cmux.

## Provider status — cmux is best-effort

- **herdr is the default and the proof-gated provider**; **cmux is best-effort** — it ships on the
  same `rig terminal <provider>` + web-launcher neighborhood, but a cmux miss is not a slice failure.
  Reach for cmux when it is specifically wanted; otherwise default to herdr (`rig terminal open <view>`
  with no `--provider`).
- Views are **provider-agnostic**: the same view + the same agents + the same semantics carry across
  herdr and cmux. A saved view opens in either.

## The surface (same three verbs, `--provider cmux`)

```bash
rig terminal open <view> --provider cmux [--json]   # open a view into cmux (herdr is the no-flag default)
rig terminal views [--json]                          # the same view library, provider-agnostic
rig terminal status --provider cmux [--json]         # cmux liveness / health
```

`<view>` resolves exactly as with herdr: a **rig name** · **`pod:<rig>/<podNamespace>`** ·
**`mission:<id>`** · **`slice:<id>`** (derived live) · a **saved-view name**.

## What carries over unchanged from openrig-herdr

All of these behave identically — see openrig-herdr for the detail:

- **Honest-partial / honest-degrade** — opened / absent / degraded, each named; partial opens exit 0,
  zero-pane exits non-zero; an http-registered host's agents degrade with the reason ("host `<id>` is
  http-registered; tiles need ssh"), never silently dropped.
- **Read-only policy** — a rig or `pod:` view is interactive; `mission:` / `slice:` views are
  read-only by construction; a saved view is per-member (`readOnly`). A read-only pane is
  `tmux attach -r` (client `readonly=1`, keystrokes physically cannot reach the agent). See openrig-herdr.
- **Safety rails (the fleet-safety rail)** — a tile is a *view* (nested `tmux attach`) of a
  daemon-owned session; never move/join/kill/re-parent a daemon-owned pane; closing a tile detaches
  one client and leaves the session untouched; never live-flip tmux options on a running seat in
  production (prove it in an isolated environment first).
- **Scroll + copy out of the box** — the daemon's terminal defaults (per-session scroll at launch +
  the server's clipboard defaults); running seats pick up wheel-scroll at their next relaunch.
- **Limits** — tile chrome v1 = a plain label; same-size panes for duplicate/multi-view membership
  (the different-size resize mismatch is an inherent tmux multi-client limit, documented not fixed).

## cmux-specific notes

- **Open-or-focus per agent** — cmux's shipped integration opens a node or focuses it if already open;
  expect focus (not a duplicate) when a seat is already tiled in cmux.
- **The shipped "Launch in cmux" affordance is preserved** (byte-compatible) and generalizes into the
  provider + view picker; opening cmux from the web launcher still works.
- **No AGPL arm's-length concern** — unlike herdr, cmux is OpenRig's shipped provider integration; the
  clean-room/never-embed rail that applies to herdr is not a cmux constraint. (This skill itself is
  still authored clean-room.)

## Saved views — provider-agnostic

Saved views are **hand-authored** in `terminal-views.yaml` (v1 has no save/write verb) and are
**provider-agnostic** — see **openrig-herdr** for the exact schema, the store facts (atomic tmp+rename,
byte-stable, at the OpenRig home root), and the derived-views-never-persisted rule. Reopen any saved
view in cmux with `rig terminal open <id> --provider cmux`. Derived views (a rig, `pod:<rig>/<pod>`,
`mission:<id>`, `slice:<id>`) are computed live and never written to the file.

© mvschwarz · Apache-2.0 · mvschwarz/openrig

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set49

rig-bundles-and-shareable-artifacts This skill covers creating, inspecting, and installing OpenRig bundles that package a rig topology with its workflow. Use it when preparing a proven setup for reuse in another environment. CX Codex +1 ★ 8,227repo stars openrig-upgrade Walks an agent through an OpenRig CLI and daemon upgrade one step at a time: inspect, mutate, observe. Useful when live seats matter. CX Codex +1 ★ 8,227repo stars openrig-software-factory This skill organizes OpenRig agent teams in software repositories. It sets up review handoffs and execution workflows between Claude Code and Codex seats. CX Codex +1 ★ 8,227repo stars openrig-skills This skill helps an agent in OpenRig find the right context for a handover, debugging, or recovery task. It also shows how to locate and load other skills with rig. CX Codex +1 ★ 8,227repo stars openrig-architect This skill helps plan an OpenRig agent team, write its specs and startup guidance, and investigate agents that behave differently from their intended roles. CX Codex +1 ★ 8,227repo stars messaging-the-human This skill covers the mechanics of an agent messaging a human through rig: filing a decision request or a quiet update, then handling the reply. CX Codex +1 ★ 8,227repo stars human-in-the-loop Classifies workflow closeouts into auto-continue, human gates, or parked states. Escalations become durable queue items with context rather than ephemeral chat pings. CX Codex +1 ★ 8,227repo stars cross-host-rig-commands This skill explains how to route OpenRig commands to registered remote hosts and interpret their results. Use it when checking transport setup or diagnosing a failed remote operation. CX Codex +1 ★ 8,227repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor