cmux AI原生终端复用器 - 为AI编码代理设计的终端分屏与浏览器自动化工具

cmux-terminal-multiplexer by aradotso/trending-skills

395 周安装量

10 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/aradotso/trending-skills --skill cmux-terminal-multiplexer

AI/机器学习开发自动化

🇨🇳中文介绍

cmux — AI 原生终端复用器

技能来自 ara.so — Daily 2026 技能集

cmux 是一个为 AI 编码代理设计的、带有可编程套接字 API 的终端复用器。它通过一个简单的 CLI 提供完整的、与 Playwright 等效的浏览器自动化、实时终端分屏管理、侧边栏状态报告以及代理团队协调功能。

cmux 的功能

终端分屏 — 创建并排或堆叠的窗格，发送命令，捕获输出
浏览器自动化 — 完整的无头 Chromium，使用基于快照的元素引用（无需 CSS 选择器）
状态侧边栏 — 用户可见的实时进度条、日志消息和图标徽章
通知 — 来自代理工作流的原生操作系统通知
代理团队 — 协调并行子代理，每个子代理都有自己可见的分屏

定位自己

cmux identify --json          # 当前窗口/工作区/窗格/表面的上下文
cmux list-panes               # 当前工作区中的所有窗格
cmux list-pane-surfaces --pane pane:1  # 窗格内的表面
cmux list-workspaces          # 当前窗口中的所有工作区（标签页）

自动设置的环境变量：

$CMUX_SURFACE_ID — 你当前的表面引用
$CMUX_WORKSPACE_ID — 你当前的工作区引用

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

发送命令并读取输出

cmux send-surface --surface surface:22 "npm run build\n"
cmux capture-pane --surface surface:22              # 当前屏幕
cmux capture-pane --surface surface:22 --scrollback  # 包含完整历史记录

cmux send-key-surface --surface surface:22 ctrl-c  # 发送按键
cmux send-key-surface --surface surface:22 enter

黄金法则：永远不要抢占焦点。 始终使用 --surface 进行目标定位。

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"   # 完成后清理

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

cmux 嵌入了完整的无头 Chromium 引擎，具有 Playwright 风格的 API。无需外部 Chrome。每个命令都通过引用来定位浏览器表面。

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

cmux --json browser open https://example.com        # 打开浏览器分屏，返回表面引用
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

捕获表面引用：

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

快照和元素引用

不使用 CSS 选择器，而是通过快照获取稳定的元素引用（e1、e2、...）：

cmux browser surface:23 snapshot --interactive              # 完整的交互式快照
cmux browser surface:23 snapshot --interactive --compact     # 紧凑输出
cmux browser surface:23 snapshot --selector "form#login" --interactive  # 限定范围

引用在 DOM 突变后失效 — 导航或点击后务必重新快照。使用 --snapshot-after 自动获取新快照：

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

# 点击和悬停
cmux browser surface:23 click e1
cmux browser surface:23 dblclick e2
cmux browser surface:23 hover e3
cmux browser surface:23 focus e4

# 文本输入
cmux browser surface:23 fill e5 "hello@example.com"   # 清空 + 输入
cmux browser surface:23 fill e5 ""                      # 清空输入框
cmux browser surface:23 type e6 "search query"          # 输入而不清空

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

# 表单
cmux browser surface:23 check e7          # 复选框
cmux browser surface:23 uncheck e7
cmux browser surface:23 select e8 "option-value"

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

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

cmux browser surface:23 get text body        # 可见文本
cmux browser surface:23 get html body        # 原始 HTML
cmux browser surface:23 get value "#email"   # 输入框的值
cmux browser surface:23 get attr "#link" --attr href
cmux browser surface:23 get count ".items"   # 元素数量
cmux browser surface:23 get box "#button"    # 边界框
cmux browser surface:23 get styles "#el" --property color

# 状态检查
cmux browser surface:23 is visible "#modal"
cmux browser surface:23 is enabled "#submit"
cmux browser surface:23 is checked "#agree"

定位器（Playwright 风格）

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

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)"

cmux browser surface:23 frame "#iframe-selector"   # 切换到 iframe
cmux browser surface:23 frame main                  # 返回主框架
cmux browser surface:23 dialog accept
cmux browser surface:23 dialog dismiss
cmux browser surface:23 dialog accept "prompt text"

Cookie、存储和状态

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

# 本地/会话存储
cmux browser surface:23 storage local get
cmux browser surface:23 storage local set myKey "myValue"
cmux browser surface:23 storage session clear

# 保存/恢复完整的浏览器状态（cookie + 存储 + 标签页）
cmux browser surface:23 state save ./auth-state.json
cmux browser surface:23 state load ./auth-state.json

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

# 保存认证信息以供重用
cmux browser $BROWSER state save ./auth-state.json

# 在新的表面中重用
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

cmux browser surface:23 console list     # JS 控制台输出
cmux browser surface:23 console clear
cmux browser surface:23 errors list      # JS 错误
cmux browser surface:23 errors clear
cmux browser surface:23 highlight "#el"  # 视觉高亮
cmux browser surface:23 screenshot       # 捕获屏幕截图

脚本和样式注入

cmux browser surface:23 addscript "console.log('injected')"
cmux browser surface:23 addstyle "body { background: red; }"
cmux browser surface:23 addinitscript "window.__injected = true"  # 每次导航时运行

侧边栏状态和进度

在不中断用户流程的情况下显示实时状态：

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"

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

使用 cmux 的代理团队

使用 cmux 分屏为每个代理团队成员提供一个可见的工作区。通过 SendMessage 和任务列表进行协调 — 切勿通过读取彼此的终端输出。

为每个团队成员创建分屏
通过 Agent 工具生成团队成员 — 将各自的 cmux 表面引用传递给他们
团队成员通过 cmux send-surface 在其分屏中运行命令
团队成员通过 cmux set-status 和 cmux log 报告状态
用户并排查看所有工作

示例：3 人代理团队

# 为每个团队成员创建可见的分屏
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'])")

然后在每个团队成员的提示中：

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.

混合布局：终端 + 浏览器

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'])")

切勿在分屏中生成 claude -p — 改为使用带有 team_name 的 Agent 工具
在生成团队成员之前创建分屏 — 在其提示中传递引用
每个团队成员一个分屏 — 各自拥有其可见的工作区
通过 SendMessage 协调，而不是通过读取彼此的终端输出
清理：完成后使用 cmux close-surface --surface <ref>

任务	命令
我在哪里？	`cmux identify --json`
向右分屏	`cmux --json new-split right`
向下分屏	`cmux --json new-split down`
发送命令	`cmux send-surface --surface <ref> "cmd\n"`
读取输出	`cmux capture-pane --surface <ref>`
打开浏览器	`cmux --json browser open <url>`
页面快照	`cmux browser <ref> snapshot --interactive`
点击元素	`cmux browser <ref> click e1`
填充输入框	`cmux browser <ref> fill e1 "text"`
等待加载	`cmux browser <ref> wait --load-state complete --timeout-ms 15000`
读取页面文本	`cmux browser <ref> get text body`
执行 JS	`cmux browser <ref> eval "expression"`
按角色查找	`cmux browser <ref> find role button`
保存认证	`cmux browser <ref> state save ./auth.json`
加载认证	`cmux browser <ref> state load ./auth.json`
设置状态	`cmux set-status <key> "text" --icon <name>`
进度条	`cmux set-progress 0.5 --label "Working..."`
日志消息	`cmux log "message"`
通知	`cmux notify --title "T" --body "B"`
关闭分屏	`cmux close-surface --surface <ref>`
屏幕截图	`cmux browser <ref> screenshot`

在后台分屏中运行构建，跟踪日志

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"
# ... 做其他工作 ...
cmux capture-pane --surface "$LOG" --scrollback | tail -20

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
# 使用 e1, e2, e3 等引用进行交互...
cmux browser $BROWSER screenshot
cmux browser $BROWSER errors list
cmux close-surface --surface $BROWSER

状态驱动的长任务

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

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

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

# ... 步骤 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"

🇺🇸English

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

Create splits for each teammate
Spawn teammates via Agent tool — pass each their cmux surface ref
Teammates run commands in their split via cmux send-surface
Teammates report status via cmux set-status and cmux log
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 spawnclaude -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

Task	Command
Where am I?	`cmux identify --json`
Split right	`cmux --json new-split right`
Split down	`cmux --json new-split down`
Send command	`cmux send-surface --surface <ref> "cmd\n"`
Read output	`cmux capture-pane --surface <ref>`
Open browser	`cmux --json browser open <url>`

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"

Weekly Installs

345

Repository

aradotso/trending-skills

GitHub Stars

First Seen

7 days ago

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

opencode341

gemini-cli340

github-copilot340

codex340

amp340

cline340

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

138,300 周安装