REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/agent-sh-agent-workspace-linux)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 agent-workspace-linux | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | agent-sh | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 221 | 463,670 | 233,682 | 148,887 | 143,987 |
| 最近代码更新 | 2026年11月15日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月16日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
agent-sh 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodex
依据开发者 README 和 repo 中的文件夹
GitHub account agent-sh (organization) is only 8 months old: take extra care
★ 221 stars, few users so far · code last changed 2026年11月15日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 50b8945 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (331). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /agent-workspace-linux,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 agent-workspace-linux 文件夹放到 ~/.agents/skills/agent-workspace-linux
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 agent-workspace-linux
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: agent-workspace-linux
description: "Use when a task needs a hidden Linux desktop running in the background or a workspace-owned browser: GUI app QA, web/browser/shopping automation, app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file edits."
---
# agent-workspace-linux
Drive an agent-owned Linux desktop and workspace-owned browser in the
background through the `agent-workspace-linux` MCP server. The workspace runs
apps, browser automation, screenshots, clipboard, and input inside its own
hidden display, never the user's real desktop, focus, or host Chrome.
It is not a sandbox. Apps you launch there run as the user, with the user's
files and network. Host runtimes also relay the keyring and SSH agent; prepared
GNOME 46 does not relay host session services. A `git push`, a sent message or a file
deleted from a workspace terminal is real. Act as carefully as on the user's
own machine. Launch Chrome through `workspace_open_browser` or with `--user-data-dir`: a plain launch would hand off to the user's running browser and is refused.
This skill is the lightweight entry point. The MCP exposes many tools; do not
load, list, or paste them all up front. Route by phase and ask the host to load
only the tool schemas needed for the next action.
## Critical Boundaries
### Use the dedicated Codex for Linux feature page for setup
Codex for Linux owns Agent Workspace setup through the **Agent Workspaces** page:
binary path, page-authored permission rules, permission file mutation,
Reconnect/Smoke test, profile creation, workspace start/stop, and viewer launch.
Do not send users to generic MCP settings, general configuration pages, or
`~/.codex/config.toml` for normal Codex for Linux setup.
Skip unless: the host is Codex for Linux and the task is setup, permission
changes, reconnect/restart, or the workspace tools are unavailable.
### Keep tools progressive
The bundled installer is skill-first. `./install.sh` installs this skill under
`~/.codex/skills` by default and leaves generic Codex MCP config untouched
unless the user explicitly chooses `--codex-configure` or `--permissions`.
For migration only, `./install.sh --clean-codex-config` removes stale generic
Codex MCP entries left by older installs; restart or reconnect Codex afterward.
Skip unless: the user asks how to install/register the backend or why the tool
family should not be loaded at startup.
### Never target the host desktop
Use this skill only for the hidden workspace. For the user's real Linux desktop,
real Chrome profile, existing tabs, or host focus/mouse/keyboard, use the
appropriate host-desktop or browser tool instead.
Skip unless: the requested action can run inside the workspace display
or workspace-owned browser.
## When To Use
- GUI app QA in a throwaway desktop.
- Browser/web/shopping automation that must not hijack host Chrome.
- Observation of workspace windows, logs, events, screenshots, or artifacts.
- Cleanup of stale or orphaned agent workspaces.
Skip unless: the user task requires running or driving a real GUI app/browser
off the user's screen. For pure code, shell, or file edits, do not start a workspace.
## Permission Model
- **Default**: no MCP ceiling is configured; the host/client owns approvals.
Call `mcp_permissions` once before mutating to confirm `configured=false`.
- **App allowlist**: `--permissions PATH` or `AGENT_WORKSPACE_PERMISSIONS`
limits which programs agents may launch, for the life of that MCP process. It can only be broadened by changing the config and
restarting/reconnecting the backend from the owning setup surface.
- **Action marks**: `mcp_action_catalog` marks each tool read-only, write,
destructive or open-world. Ask the user before destructive or open-world
actions they did not request.
- **Live control**: `mcp_control_state` read-only/paused/active is a
best-effort runtime control, not the authoritative boundary.
- **Real-world actions**: checkout, purchases, account changes, and messages
require explicit user approval. Keep drafting separate from final action.
Skip unless: you are about to start a workspace, open a profile, launch/run an
app, send input, or act on an external account/site.
## Phase Router
Always orient before mutating.
| Phase | Load only these tools |
| --- | --- |
| Orient | `mcp_agent_context`, `mcp_session_brief`, `mcp_task_plan`, `mcp_permissions`, `mcp_action_catalog`, `workspace_doctor`, `workspace_list`, `workspace_status` |
| Profiles | `profile_list`, `profile_get`, `profile_template`, `profile_put`, `profile_check` |
| Start | `workspace_start`, `workspace_open_profile` |
| Observe | `workspace_observe`, `workspace_screenshot`, `workspace_list_windows`, `workspace_active_window`, `workspace_read_app_log`, `workspace_events` |
| Act | `workspace_launch_app`, `workspace_run_app`, `workspace_click`, `workspace_type_text`, `workspace_key`, `workspace_paste_text`, `workspace_focus_window`, `workspace_close_window` |
| Browser | `workspace_open_browser`, `workspace_browser_targets`, `workspace_browser_snapshot`, `workspace_browser_navigate`, `workspace_browser_search_results`, `workspace_browser_click` |
| Viewer/control | `mcp_control_state`, `mcp_control_update`, `workspace_open_viewer`, `workspace_list_viewers`, `workspace_close_viewer` |
| Teardown | `workspace_stop`, `workspace_kill_app`, `workspace_cleanup_stale` |
Skip unless: the current phase needs one of the listed capabilities. Do not load
schemas for later phases until the plan reaches them.
## Safe Workflow
1. Orient: call `mcp_agent_context` or `mcp_session_brief`, then use
`mcp_task_plan` for app-QA, browser, observe, or cleanup intent.
2. Check permissions: call `mcp_permissions` before mutating.
3. Start: use `workspace_start` with `ack_hidden_workspace=true` and a clear
`purpose`, or `workspace_open_profile` for a saved profile.
4. Observe: use `workspace_observe` or focused screenshot/window/log/event
tools before sending input.
5. Act: launch apps, run commands, click/type/paste/key only inside the
workspace.
6. Stop: use `workspace_stop` when finished; use `workspace_cleanup_stale` for
orphaned runtimes.
Session selection supports X11 (`Xvfb` + Openbox), i3 on private Xvfb, and
native Wayland sessions on KWin, GNOME, Hyprland and COSMIC. MCP callers pass
`session: {"backend":"<name>"}` with one of `x11`, `kwin`, `gnome`, `i3`,
`hyprland` or `cosmic`, and may add `"scale":1.5` on the native Wayland
backends for 150% output scaling. CLI start/open-profile accepts the same
names with `--session NAME --scale 1.5`. Explicit MCP input overrides the
profile session; omitting both keeps the pinned X11 default.
KWin needs version 6.6 or newer, kwin-common, kscreen-doctor, wl-clipboard,
and an accessible DRM render node. It runs directly, without a parent Xvfb, and
is not a full Plasma shell. GNOME runs GNOME Shell 50 or 51 with a private
headless output and software rendering; Mutter accepts only scales the chosen
output mode supports. Hyprland uses a private KWin renderer and supports
fractional output scales; see [the Hyprland backend guide](../../docs/hyprland.md).
COSMIC runs `cosmic-comp` under a software-only private Weston parent; see
[the COSMIC guide](../../docs/native-cosmic.md) for its compositor and
XWayland dependencies.
Select i3 with `session: {"backend":"i3"}` or `--session i3`. It uses scale 1,
needs `i3-wm` and the X11 dependencies including ImageMagick `import`, and has
no launcher bindings or startup commands. Move and resize float the target window.
Minimize uses the scratchpad; show restores the window to the current workspace.
Pointer and window coordinates use screenshot pixels on every backend.
Unsupported session names are rejected.
For a prepared GNOME 46 userspace, pass
`session: {"backend":"gnome","version":"46","scale":1.25}` or
`--session gnome --session-提问、分享技巧或报告无法使用。按“有帮助”数量排序。