cmux — AI-Native Terminal Multiplexer

Skill by ara.so — Daily 2026 Skills collection

cmux is a terminal multiplexer with a programmable socket API designed for AI coding agents. It provides full Playwright-equivalent browser automation, real-time terminal split management, sidebar status reporting, and agent team coordination — all via a simple CLI.

What cmux Does

• Terminal splits — create side-by-side or stacked panes, send commands, capture output
• Browser automation — full headless Chromium with snapshot-based element refs (no CSS selectors)
• Status sidebar — live progress bars, log messages, and icon badges visible to the user
• Notifications — native OS notifications from agent workflows
• Agent teams — coordinate parallel subagents, each with their own visible split

Orient Yourself

cmux identify --json          # current window/workspace/pane/surface context
cmux list-panes               # all panes in current workspace
cmux list-pane-surfaces --pane pane:1  # surfaces within a pane
cmux list-workspaces          # all workspaces (tabs) in current window

Environment variables set automatically:

• $CMUX_SURFACE_ID — your current surface ref
• $CMUX_WORKSPACE_ID — your current workspace ref

Handles use short refs: surface:N, pane:N, workspace:N, window:N.

Terminal Splits

Create splits

cmux --json new-split right   # side-by-side (preferred for parallel work)
cmux --json new-split down    # stacked (good for logs)

Always capture the returned surface_ref:

WORKER=$(cmux --json new-split right | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")

Send commands and read output

cmux send-surface --surface surface:22 "npm run build\n"
cmux capture-pane --surface surface:22              # current screen
cmux capture-pane --surface surface:22 --scrollback  # with full history

cmux send-key-surface --surface surface:22 ctrl-c  # send key
cmux send-key-surface --surface surface:22 enter

Golden rule: never steal focus. Always use --surface targeting.

Worker split pattern

WORKER=$(cmux --json new-split right | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
cmux send-surface --surface "$WORKER" "make test 2>&1; echo EXIT_CODE=\$?\n"
sleep 3
cmux capture-pane --surface "$WORKER"
cmux close-surface --surface "$WORKER"   # clean up when done

Pane management

cmux focus-pane --pane pane:2
cmux close-surface --surface surface:22
cmux swap-pane --pane pane:1 --target-pane pane:2
cmux move-surface --surface surface:7 --pane pane:2 --focus true
cmux reorder-surface --surface surface:7 --before surface:3

Browser Automation

cmux embeds a full headless Chromium engine with a Playwright-style API. No external Chrome required. Every command targets a browser surface by ref.

Workflow pattern

navigate → wait for load → snapshot --interactive → act with refs → re-snapshot

Open and navigate

cmux --json browser open https://example.com        # opens browser split, returns surface ref
cmux browser surface:23 goto https://other.com
cmux browser surface:23 back
cmux browser surface:23 forward
cmux browser surface:23 reload
cmux browser surface:23 get url
cmux browser surface:23 get title

Capture the surface ref:

BROWSER=$(cmux --json browser open https://docs.example.com | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")

Snapshot and element refs

Instead of CSS selectors, snapshot to get stable element refs (e1, e2, ...):

cmux browser surface:23 snapshot --interactive              # full interactive snapshot
cmux browser surface:23 snapshot --interactive --compact     # compact output
cmux browser surface:23 snapshot --selector "form#login" --interactive  # scoped

Refs are invalidated after DOM mutations — always re-snapshot after navigation or clicks. Use --snapshot-after to auto-get a fresh snapshot:

cmux --json browser surface:23 click e1 --snapshot-after

Interact with elements

# Click and hover
cmux browser surface:23 click e1
cmux browser surface:23 dblclick e2
cmux browser surface:23 hover e3
cmux browser surface:23 focus e4

# Text input
cmux browser surface:23 fill e5 "hello@example.com"   # clear + type
cmux browser surface:23 fill e5 ""                      # clear input
cmux browser surface:23 type e6 "search query"          # type without clearing

# Keys
cmux browser surface:23 press Enter
cmux browser surface:23 press Tab
cmux browser surface:23 keydown Shift

# Forms
cmux browser surface:23 check e7          # checkbox
cmux browser surface:23 uncheck e7
cmux browser surface:23 select e8 "option-value"

# Scroll
cmux browser surface:23 scroll --dy 500
cmux browser surface:23 scroll --selector ".container" --dy 300
cmux browser surface:23 scroll-into-view e9

Wait for state

cmux browser surface:23 wait --load-state complete --timeout-ms 15000
cmux browser surface:23 wait --selector "#ready" --timeout-ms 10000
cmux browser surface:23 wait --text "Success" --timeout-ms 10000
cmux browser surface:23 wait --url-contains "/dashboard" --timeout-ms 10000
cmux browser surface:23 wait --function "document.readyState === 'complete'" --timeout-ms 10000

Read page content

cmux browser surface:23 get text body        # visible text
cmux browser surface:23 get html body        # raw HTML
cmux browser surface:23 get value "#email"   # input value
cmux browser surface:23 get attr "#link" --attr href
cmux browser surface:23 get count ".items"   # element count
cmux browser surface:23 get box "#button"    # bounding box
cmux browser surface:23 get styles "#el" --property color

# State checks
cmux browser surface:23 is visible "#modal"
cmux browser surface:23 is enabled "#submit"
cmux browser surface:23 is checked "#agree"

Locators (Playwright-style)

cmux browser surface:23 find role button
cmux browser surface:23 find text "Sign In"
cmux browser surface:23 find label "Email"
cmux browser surface:23 find placeholder "Enter email"
cmux browser surface:23 find testid "submit-btn"
cmux browser surface:23 find first ".item"
cmux browser surface:23 find last ".item"
cmux browser surface:23 find nth ".item" 3

JavaScript evaluation

cmux browser surface:23 eval "document.title"
cmux browser surface:23 eval "document.querySelectorAll('.item').length"
cmux browser surface:23 eval "window.scrollTo(0, document.body.scrollHeight)"

Frames and dialogs

cmux browser surface:23 frame "#iframe-selector"   # switch to iframe
cmux browser surface:23 frame main                  # back to main frame
cmux browser surface:23 dialog accept
cmux browser surface:23 dialog dismiss
cmux browser surface:23 dialog accept "prompt text"

Cookies, storage, and state

# Cookies
cmux browser surface:23 cookies get
cmux browser surface:23 cookies set session_token "abc123"
cmux browser surface:23 cookies clear

# Local/session storage
cmux browser surface:23 storage local get
cmux browser surface:23 storage local set myKey "myValue"
cmux browser surface:23 storage session clear

# Save/restore full browser state (cookies + storage + tabs)
cmux browser surface:23 state save ./auth-state.json
cmux browser surface:23 state load ./auth-state.json

Authentication flow

BROWSER=$(cmux --json browser open https://app.example.com/login | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
cmux browser $BROWSER wait --load-state complete --timeout-ms 15000
cmux browser $BROWSER snapshot --interactive
cmux browser $BROWSER fill e1 "user@example.com"
cmux browser $BROWSER fill e2 "my-password"
cmux browser $BROWSER click e3
cmux browser $BROWSER wait --url-contains "/dashboard" --timeout-ms 20000

# Save auth for reuse
cmux browser $BROWSER state save ./auth-state.json

# Reuse in a new surface
BROWSER2=$(cmux --json browser open https://app.example.com | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
cmux browser $BROWSER2 state load ./auth-state.json
cmux browser $BROWSER2 goto https://app.example.com/dashboard

Diagnostics

cmux browser surface:23 console list     # JS console output
cmux browser surface:23 console clear
cmux browser surface:23 errors list      # JS errors
cmux browser surface:23 errors clear
cmux browser surface:23 highlight "#el"  # visual highlight
cmux browser surface:23 screenshot       # capture screenshot

Script and style injection

cmux browser surface:23 addscript "console.log('injected')"
cmux browser surface:23 addstyle "body { background: red; }"
cmux browser surface:23 addinitscript "window.__injected = true"  # runs on every nav

Sidebar Status and Progress

Show live status to the user without interrupting their flow:

cmux set-status agent "working" --icon hammer --color "#ff9500"
cmux set-status agent "done" --icon checkmark --color "#34c759"
cmux clear-status agent

cmux set-progress 0.3 --label "Running tests..."
cmux set-progress 1.0 --label "Complete"
cmux clear-progress

cmux log "Starting build"
cmux log --level success "All tests passed"
cmux log --level error --source build "Compilation failed"

Notifications

cmux notify --title "Task Complete" --body "All tests passing"
cmux notify --title "Need Input" --subtitle "Permission" --body "Approve deployment?"

Agent Teams with cmux

Use cmux splits to give each agent teammate a visible workspace. Coordinate via SendMessage and task lists — never via reading each other's terminal output.

The pattern

1. Create splits for each teammate
2. Spawn teammates via Agent tool — pass each their cmux surface ref
3. Teammates run commands in their split via cmux send-surface
4. Teammates report status via cmux set-status and cmux log
5. User sees all work side-by-side

Example: 3-agent team

# Create visible splits for each teammate
SPLIT_1=$(cmux --json new-split right | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
SPLIT_2=$(cmux --json new-split down | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
SPLIT_3=$(cmux --json new-split down | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")

Then in each teammate's prompt:

You have a cmux terminal split at surface:42.
Run commands:  cmux send-surface --surface surface:42 "command\n"
Read output:   cmux capture-pane --surface surface:42
Set status:    cmux set-status myagent "working" --icon hammer
Log progress:  cmux log "message"
Never steal focus — always use --surface targeting.

Mixed layout: terminals + browsers

BUILD=$(cmux --json new-split right | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
DOCS=$(cmux --json browser open https://docs.example.com | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
TEST=$(cmux --json new-split down | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")

Key rules

• Never spawn claude -p in splits — use the Agent tool with team_name instead
• Create splits before spawning teammates — pass refs in their prompts
• One split per teammate — each owns their visible workspace
• Coordinate via SendMessage, not by reading each other's terminal output
• Clean up: cmux close-surface --surface <ref> when done

Quick Reference

Common Patterns

Run build in background split, tail logs

LOG=$(cmux --json new-split down | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
cmux send-surface --surface "$LOG" "cargo build --release 2>&1 | tee /tmp/build.log\n"
# ... do other work ...
cmux capture-pane --surface "$LOG" --scrollback | tail -20

QA test flow

BROWSER=$(cmux --json browser open https://myapp.vercel.app | python3 -c "import sys,json; print(json.load(sys.stdin)['surface_ref'])")
cmux browser $BROWSER wait --load-state complete --timeout-ms 15000
cmux browser $BROWSER snapshot --interactive
# Interact using e1, e2, e3 refs...
cmux browser $BROWSER screenshot
cmux browser $BROWSER errors list
cmux close-surface --surface $BROWSER

Status-driven long task

cmux set-status task "starting" --icon clock --color "#ff9500"
cmux set-progress 0.0 --label "Initializing..."

# ... step 1 ...
cmux set-progress 0.33 --label "Building..."

# ... step 2 ...
cmux set-progress 0.66 --label "Testing..."

# ... step 3 ...
cmux set-progress 1.0 --label "Done"
cmux set-status task "complete" --icon checkmark --color "#34c759"
cmux clear-progress
cmux notify --title "Task complete" --body "All steps passed"