A terminal session manager for coordinating several command-line sessions and watching their output. It supports workflows involving Claude Code, Cursor, and Codex.

Creating and inspecting terminal workspaces, panes, and surfaces; running parallel commands; monitoring output; and reporting progress when working inside cmux.

It keeps parallel terminal work organized and makes it easier to monitor multiple running commands or agent sessions.

cmux — Skill for Claude Code and Codex by boundsj/agent-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add boundsj/agent-skills --skill cmux

Clone the repo

git clone --depth 1 https://github.com/boundsj/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/boundsj/agent-skills/cmux/github.svg)](https://agentmods.dev/skills/boundsj/agent-skills/cmux)

Your own site

<a href="https://agentmods.dev/skills/boundsj/agent-skills/cmux"><img src="https://agentmods.dev/badge/skills/boundsj/agent-skills/cmux/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/boundsj/agent-skills/cmux"><img src="https://agentmods.dev/badge/skills/boundsj/agent-skills/cmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,394 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.05394
Opus 5.5	$0.00013	$0.02158
Sonnet 5.5	$0.00007	$0.01079
Haiku 4.5	$0.00003	$0.00539

Measured 2mo ago against content hash 51963f864556, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cmux scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cmux/SKILL.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cmux Terminal Multiplexer — Agent Integration

Use when orchestrating terminal sessions, running parallel commands, monitoring output, or reporting progress inside cmux. Works for Claude Code, Cursor, and Codex.

Detection

Check for the CMUX_WORKSPACE_ID environment variable. If set, you are inside cmux and can use the cmux CLI. If unset, do NOT attempt any cmux commands.

The CLI binary is at /Applications/cmux.app/Contents/Resources/bin/cmux (also available as cmux on PATH inside cmux terminals).

Environment variables automatically set in cmux terminals:

CMUX_WORKSPACE_ID — current workspace ref
CMUX_SURFACE_ID — current surface ref
CMUX_SOCKET_PATH — Unix socket path (usually /tmp/cmux.sock)

Hierarchy

Window > Workspace (sidebar tab) > Pane (split region) > Surface (terminal tab in pane).

Use short refs: workspace:1, pane:1, surface:2.

Core Commands

Orientation

cmux identify --json              # get caller context (workspace/surface/pane refs)
cmux list-workspaces              # list all workspaces
cmux list-panes                   # list panes in current workspace
cmux list-pane-surfaces --pane <ref>  # list surfaces (tabs) in a pane

Create Terminals

cmux new-workspace --command "cd /path && cmd"  # new workspace tab (does NOT switch to it)
cmux new-split <left|right|up|down>             # split current pane
cmux new-surface                                # new tab in current pane
cmux new-pane --direction <dir>                 # new pane

Send Input / Read Output

cmux send --surface <ref> "text\n"          # send text to a surface (include \n for enter)
cmux send-key --surface <ref> <key>         # send key (enter, ctrl-c, etc.)
cmux read-screen --surface <ref> --lines <n>  # read terminal output (last n lines)

Progress Reporting (shows in cmux sidebar)

cmux set-status <key> <value> --icon <name> --color <#hex>
cmux set-progress <0.0-1.0> --label "text"
cmux log --level <info|success|warning|error> --source "agent" -- "message"
cmux notify --title "Title" --body "Body"   # desktop notification
cmux clear-status <key>
cmux clear-progress
cmux clear-log

Read the full file on GitHub · 469 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 469 lines · 33 tokens per session scan A 51963f864556

Subscribe to this mod's changes

cmux is a skill published in the GitHub repository boundsj/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 5,394 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud

cmux next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cmuxboundsj/agent-skills	Skill	2	4mo ago	MIT	A	33	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex