Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linux --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-workspace-linux .claude/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .claude/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linuxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linux --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-workspace-linux .agents/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .agents/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linux --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-workspace-linux .cursor/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .cursor/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agent-sh/agent-workspace-linux.git --path skills/agent-workspace-linux--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linux --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-workspace-linux .gemini/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .gemini/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linuxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-workspace-linux .github/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .github/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agent-sh/agent-workspace-linux agent-workspace-linux --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agent-sh/agent-workspace-linux.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-workspace-linux .opencode/skills/agent-workspace-linux && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-workspace-linux" agent skill from https://github.com/agent-sh/agent-workspace-linux/tree/main/skills/agent-workspace-linux into .opencode/skills/agent-workspace-linux/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-workspace-linux", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
agent-workspace-linuxDrives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.
Apps, browser automation, screenshots, clipboard and input all run inside the workspace's own hidden display, never on your real desktop, focus or Chrome profile. The skill is a light entry point to the `agent-workspace-linux` MCP server: because the server exposes many tools, the agent routes by phase and asks the host to load only the tool schemas needed next.
It fits GUI application QA in a throwaway desktop, browser, web and shopping automation that must not hijack host Chrome, observing sandboxed windows, logs, events, screenshots and artifacts, and cleaning up stale or orphaned workspaces. It is not for the host desktop or Chrome, generic MCP setup, or pure code and file edits. Setup on Codex for Linux belongs to its Agent Workspaces page, covering binary path, permission rules, reconnecting and smoke tests, profiles, starting and stopping workspaces and the viewer, not generic MCP settings. The installer puts the skill under `~/.codex/skills` and leaves the Codex MCP config alone unless `--codex-configure` or `--permissions` is chosen.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 39f2473. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
cursorcodexFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Isolated Linux Agent Workspace loads about 2.1k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 981 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from agent-sh/agent-workspace-linux at commit 39f2473, republished under its MIT licence (© agent-sh). 981 words, ~2,121 tokens.
.claude/skills/agent-workspace-linux/SKILL.md (or your agent's skills folder).Drive an isolated, agent-owned Linux desktop and workspace-owned browser 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.
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.
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.
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.
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 isolated workspace display or workspace-owned browser.
Skip unless: the user task requires running or driving a real GUI app/browser in isolation. For pure code, shell, or file edits, do not start a workspace.
mcp_permissions once before mutating to confirm configured=false.--permissions PATH or
AGENT_WORKSPACE_PERMISSIONS caps network, mounts, and app allowlist 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.mcp_control_state read-only/paused/active is a
best-effort runtime control, not the authoritative security boundary.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.
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.
mcp_agent_context or mcp_session_brief, then use
mcp_task_plan for app-QA, browser, observe, or cleanup intent.mcp_permissions before mutating.workspace_start with ack_hidden_workspace=true and a clear
purpose, or workspace_open_profile for a saved profile.workspace_observe or focused screenshot/window/log/event
tools before sending input.workspace_stop when finished; use workspace_cleanup_stale for
orphaned runtimes.Skip unless: each step's precondition is visible in the previous tool result (workspace id, app id, target window, browser target, or explicit user approval).
Use the workspace-owned browser over its loopback DevTools endpoint. Start with
workspace_open_browser, discover pages with workspace_browser_targets, read
with workspace_browser_snapshot or workspace_browser_search_results, then
navigate or click with browser tools.
Browser tools require a Chrome launched with --user-data-dir and loopback
DevTools. Always get it from workspace_open_browser (MCP) or
workspace open-browser (CLI) rather than hand-rolling a workspace_launch_app
argv.
If you attach your own CDP/WebSocket client to that endpoint, omit the Origin
header (e.g. websocket-client's suppress_origin=True). The DevTools port is
ephemeral, so Chrome's origin allow-list cannot be pre-seeded and an Origin-
bearing handshake is rejected with 403 Forbidden.
After workspace_browser_navigate or workspace_browser_click, read
page.url / page.title for post-action state. target.* is refreshed to match,
but if the refresh fails the response carries a warning saying it may be stale —
check warnings before trusting target for verification.
Skip unless: the task is web/browser automation that can run in the isolated workspace. Do not attach to host Chrome, Playwright, or Computer Use as a shortcut.
ack_hidden_workspace=true and a purpose.Task: "QA the settings dialog of myapp."
mcp_agent_context and mcp_task_plan for app-QA.mcp_permissions to confirm the active boundary.workspace_start with ack_hidden_workspace=true and purpose
"QA myapp settings".workspace_launch_app with the app command.workspace_observe to find the window.workspace_click / workspace_type_text to exercise Settings.workspace_screenshot and workspace_read_app_log for evidence.workspace_stop.allowed-tools intentionally: different hosts namespace MCP tools
differently, and the skill routes the full family progressively.agnix --target generic|claude-code|cursor|codex|kiro
when changing this file.© agent-sh, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/agent-workspace-linux of agent-sh/agent-workspace-linux.
Open the folder on GitHubat commit 39f2473
Isolated Linux Agent Workspace next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Isolated Linux Agent Workspace this skillagent-sh/agent-workspace-linux | 185 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Browser MCP Agentantibrow/anti-detect-browser-skills | 914 | 1 repos | ~4.2k | Automated safety check: Warn | MIT | |
| Lightpandalightpanda-io/agent-skill | 101 | — | ~6k | Automated safety check: Pass | Apache-2.0 | |
| Linux Desktop Controlagent-sh/computer-use-linux | 661 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Altic Studioaltic-dev/altic-mcp | 172 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Computer Usexuzhougeng/wisp-science | 1k | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 |
antibrow/anti-detect-browser-skills
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…
lightpanda-io/agent-skill
Lightpanda browser, drop-in replacement for Chrome-based browsing in any AI agent - faster and lighter for tasks without graphical rendering like data retrieval.
agent-sh/computer-use-linux
Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input.
altic-dev/altic-mcp
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
xuzhougeng/wisp-science
Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux.
AIPexStudio/AIPex
Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads.
Works with
Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop. Apps, browser automation, screenshots, clipboard and input all run inside the workspace's own hidden display, never on your real desktop, focus or Chrome profile. The skill is a light entry point to the `agent-workspace-linux` MCP server: because the server exposes many tools, the agent routes by phase and asks the host to load only the tool schemas needed next.
Isolated Linux Agent Workspace fits situations like: testing a GUI application in a disposable desktop; automating a web or shopping task without using the real Chrome; observing a sandboxed app through screenshots and logs; cleaning up stale agent workspaces.
Run `npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a claude-code`. Or copy the skill folder (skills/agent-workspace-linux in agent-sh/agent-workspace-linux) into .claude/skills/agent-workspace-linux in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a codex`. Or copy the skill folder (skills/agent-workspace-linux in agent-sh/agent-workspace-linux) into .agents/skills/agent-workspace-linux in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agent-sh/agent-workspace-linux --skill agent-workspace-linux -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-workspace-linux, .gemini/skills/agent-workspace-linux, .github/skills/agent-workspace-linux and .opencode/skills/agent-workspace-linux in your project.
Going by SKILL.md and its folder, Isolated Linux Agent Workspace needs the command-line tools its instructions call (cursor and codex). Our summary lists: The agent-workspace-linux MCP server; A Linux host.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Isolated Linux Agent Workspace is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Isolated Linux Agent Workspace: Browser MCP Agent (antibrow/anti-detect-browser-skills, 914 stars), Lightpanda (lightpanda-io/agent-skill, 101 stars), Linux Desktop Control (agent-sh/computer-use-linux, 661 stars) and Altic Studio (altic-dev/altic-mcp, 172 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agent-sh (a GitHub organization) maintains it in agent-sh/agent-workspace-linux, which has 185 GitHub stars. The repository was last updated on October 3, 2026.
Source: agent-sh/agent-workspace-linux on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
