Update to Cloud Environment
Snapshot Nov 14, 2026 · 00:16 UTC · version 0.2.1
Collection source: downloaded plugin package.
Instructions updated for cloud-desktop
Full description — Now says: Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools.
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Nov 7, 2026 · 06:11 UTC
Use in a managed Codex Cloud chat to open a URL in shared Chrome, inspect a Linux app, show the Desktop panel, or diagnose missing computer-use tools.
Nov 14, 2026 · 00:16 UTC
Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools.
Skill instructions
Nov 7, 2026 · 06:11 UTC
Use in a managed Codex Cloud chat to open a URL in shared Chrome, inspect a Linux app, show the Desktop panel, or diagnose missing computer-use tools. # Use the shared cloud desktop When the chat’s environment context identifies a manage...
Nov 14, 2026 · 00:16 UTC
Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools. Use the attached desktop for hands-on work in a Cloud app, even with the Deskt...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,52 +1,34 @@ --- name: cloud-desktop -description: Use in a managed Codex Cloud chat to open a URL in shared Chrome, inspect a Linux app, show the Desktop panel, or diagnose missing computer-use tools. +description: Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools. --- -# Use the shared cloud desktop +Use the attached desktop for hands-on work in a Cloud app, even with the Desktop panel closed. “Try signup and tell me what appears after Submit” or “capture this signed-in tab” calls for the actual browser session. Use the project’s test runner for “run the signup suite.” Use headless automation for repeatable checks such as screenshots at several viewport sizes. If the result depends on a visible window or an existing session, use the browser that reproduces that condition. -When the chat’s environment context identifies a managed cloud executor, use -its Chrome for “open this URL” or “check in the browser” unless the user -names another browser or device. - -Chrome and native apps share one Linux display (X11). Codex can use the -computer-use tools with the Desktop panel closed. Opening the panel lets the -user watch and take control of the same screen. Closing it disconnects the -viewer and leaves the desktop running. - -## What starts on demand - -On an on-demand desktop, Codex can discover the tools and check status while -the display stays asleep. The first valid desktop `js` call starts the display -before running the code. Connecting the Desktop viewer also starts it. -Chrome has its own startup setting. When configured to start closed, it -launches on the first browser operation that needs it, such as opening a tab. +For a broad request like “test signup,” choose the checks that answer the question. If the form shows an error after submission, an API or regression check can help distinguish a display problem from a failed signup. Report what each check established. + +Use the browser, tab, or device the user names. If they leave the choice to you, open a Cloud app in shared Chrome at its local URL, such as `http://127.0.0.1:3000`, even when forwarding to the user’s browser is unavailable. For an external URL with no browser specified, follow the available browser tool’s selection instructions. ## Open and inspect -Look for the desktop JavaScript tool (usually `cua_repl.js`) among the tools -offered directly to this turn. Follow its first-call instructions. For a new -tab in Chrome, `await cua.createBrowserTab("cdp", url)` can be the first -action when offered, even with the panel closed. -Use `await cua.getState()` to discover available browsers and apps. For an -existing tab, follow the runtime’s tab-selection or claiming instructions. -Inspect the page before reporting what loaded. Use Sky for native windows -or a full-screen screenshot when available. - -## Show the user - -When the user asks to watch or needs to act, such as completing sign-in, call -`open_in_codex({"target":{"type":"cloud-desktop"}})` if offered. In supported -Codex desktop chats, the user can also open the right side panel and choose -**New tab (+) → Desktop**. Let the user **Take over** and select **Return -control** when finished. Pause agent input during the handoff, then inspect -the same page before continuing. - -## If control is unavailable - -Call `cloud_environment.environment_status({})` and match its `environment_id` -to the selected executor. Check `capabilities[].remote_desktop`. A cold desktop -can report `enabled: true` with `state: unknown`. If the environment is -starting, recheck the tools once it is ready. Report the environment ID, -desktop status, and which tool was missing or which call failed. Say what -you could verify. If only the viewer works, offer to open it for the user. +Use the running app if it is ready. To start it, follow the environment’s **Start skill** and its readiness check when available, or use the project’s usual command and verify it responds. When starting an app, avoid managed browser ports such as `8000` and `8085`, even if they appear free. If the app’s port conflicts, use the project’s supported port override and verify the app responds on the new port. For a UI fix, reproduce the problem when possible and repeat those steps after the change. Use the Linux desktop for native windows, file pickers, or flows that cross apps. For example, open an exported PDF to check its layout. + +For the Cloud desktop, follow the first-call instructions on the desktop JavaScript tool offered for this turn (usually `cua_repl.js`). To open a new tab in shared Chrome, use `await cua.createBrowserTab("cdp", url)` when offered. To find an existing tab or app, use `await cua.getState()` and follow the tool’s tab selection or claiming instructions. Use Sky when available for a native window or a screenshot of the whole desktop. Inspect what loaded before reporting success. + +If the user requests a recording, use a recorder that can capture the chosen tab or window. Keep sign-in and credentials out of the footage. Play back the saved video to verify it shows the requested steps, then link the file in this chat. + +## Let the user watch or take over + +When the user asks to see the app or needs to act, open the viewer with `open_in_codex({"target":{"type":"cloud-desktop"}})` if offered. In supported Codex desktop chats, the user can also choose **New tab (+) → Desktop** in the right panel. For sign-in or another handoff, have the user select **Take over** and pause your input. After they select **Return control**, inspect the same screen before continuing. Closing the panel leaves the desktop running. + +## Open the app in the user’s own browser + +If the user wants the running app on their computer, verify its local port on the Cloud machine. When offered, call `open_cloud_preview` with that port and return its `localUrl`. The URL works only on the user’s computer and the app handles its own login. To share with someone else, use a supported sharing or deployment route for the intended audience. + +## If the desktop is unavailable + +Check `capabilities[].remote_desktop` in `cloud_environment.environment_status({})` if the returned `environment_id` matches this desktop. An on-demand desktop can show `enabled: true` and `state: unknown` until first use. The first valid desktop JavaScript call or a viewer connection starts the display. Chrome can start separately when an operation needs a tab. + +If the environment is starting, recheck its tools when ready. If only the viewer works, offer to open it. For a check that another browser can reproduce, try the project’s browser runner or another available browser tool and state what it verified. If the task needs the original tab, native window, or a handoff, report which interaction is blocked, the environment ID, and the missing tool or error. + +If the viewer connects but Chrome fails to start, native windows may still work. If Chrome opens but a site fails to load, compare the same URL with the shell’s configured HTTP client. Report which path failed before proposing a network change.
Full technical diff · 2 changed fields
changed /description
"Use in a managed Codex Cloud chat to open a URL in shared Chrome, inspect a Linux app, show the Desktop panel, or diagnose missing computer-use tools."
"Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools."
changed /skill_md_contents
"---\nname: cloud-desktop\ndescription: Use in a managed Codex Cloud chat to open a URL in shared Chrome, inspect a Linux app, show the Desktop panel, or diagnose missing computer-use tools.\n---\n\n# Use the shared cloud desktop\n\nWhen the chat’s environment context identifies a managed cloud executor, use\nits Chrome for “open this URL” or “check in the browser” unless the user\nnames another browser or device.\n\nChrome and native apps share one Linux display (X11). Codex can use the\ncomputer-use tools with the Desktop panel closed. Opening the panel lets the\nuser watch and take control of the same screen. Closing it disconnects the\nviewer and leaves the desktop running.\n\n## What starts on demand\n\nOn an on-demand desktop, Codex can discover the tools and check status while\nthe display stays asleep. The first valid desktop `js` call starts the display\nbefore running the code. Connecting the Desktop viewer also starts it.\nChrome has its own startup setting. When configured to start closed, it\nlaunches on the first browser operation that needs it, such as opening a tab.\n\n## Open and inspect\n\nLook for the desktop JavaScript tool (usually `cua_repl.js`) among the tools\noffered directly to this turn. Follow its first-call instructions. For a new\ntab in Chrome, `await cua.createBrowserTab(\"cdp\", url)` can be the first\naction when offered, even with the panel closed.\nUse `await cua.getState()` to discover available browsers and apps. For an\nexisting tab, follow the runtime’s tab-selection or claiming instructions.\nInspect the page before reporting what loaded. Use Sky for native windows\nor a full-screen screenshot when available.\n\n## Show the user\n\nWhen the user asks to watch or needs to act, such as completing sign-in, call\n`open_in_codex({\"target\":{\"type\":\"cloud-desktop\"}})` if offered. In supported\nCodex desktop chats, the user can also open the right side panel and choose\n**New tab (+) → Desktop**. Let the user **Take over** and select **Return\ncontrol** when finished. Pause agent input during the handoff, then inspect\nthe same page before continuing.\n\n## If control is unavailable\n\nCall `cloud_environment.environment_status({})` and match its `environment_id`\nto the selected executor. Check `capabilities[].remote_desktop`. A cold desktop\ncan report `enabled: true` with `state: unknown`. If the environment is\nstarting, recheck the tools once it is ready. Report the environment ID,\ndesktop status, and which tool was missing or which call failed. Say what\nyou could verify. If only the viewer works, offer to open it for the user.\n""---\nname: cloud-desktop\ndescription: Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools.\n---\n\nUse the attached desktop for hands-on work in a Cloud app, even with the Desktop panel closed. “Try signup and tell me what appears after Submit” or “capture this signed-in tab” calls for the actual browser session. Use the project’s test runner for “run the signup suite.” Use headless automation for repeatable checks such as screenshots at several viewport sizes. If the result depends on a visible window or an existing session, use the browser that reproduces that condition.\n\nFor a broad request like “test signup,” choose the checks that answer the question. If the form shows an error after submission, an API or regression check can help distinguish a display problem from a failed signup. Report what each check established.\n\nUse the browser, tab, or device the user names. If they leave the choice to you, open a Cloud app in shared Chrome at its local URL, such as `http://127.0.0.1:3000`, even when forwarding to the user’s browser is unavailable. For an external URL with no browser specified, follow the available browser tool’s selection instructions.\n\n## Open and inspect\n\nUse the running app if it is ready. To start it, follow the environment’s **Start skill** and its readiness check when available, or use the project’s usual command and verify it responds. When starting an app, avoid managed browser ports such as `8000` and `8085`, even if they appear free. If the app’s port conflicts, use the project’s supported port override and verify the app responds on the new port. For a UI fix, reproduce the problem when possible and repeat those steps after the change. Use the Linux desktop for native windows, file pickers, or flows that cross apps. For example, open an exported PDF to check its layout.\n\nFor the Cloud desktop, follow the first-call instructions on the desktop JavaScript tool offered for this turn (usually `cua_repl.js`). To open a new tab in shared Chrome, use `await cua.createBrowserTab(\"cdp\", url)` when offered. To find an existing tab or app, use `await cua.getState()` and follow the tool’s tab selection or claiming instructions. Use Sky when available for a native window or a screenshot of the whole desktop. Inspect what loaded before reporting success.\n\nIf the user requests a recording, use a recorder that can capture the chosen tab or window. Keep sign-in and credentials out of the footage. Play back the saved video to verify it shows the requested steps, then link the file in this chat.\n\n## Let the user watch or take over\n\nWhen the user asks to see the app or needs to act, open the viewer with `open_in_codex({\"target\":{\"type\":\"cloud-desktop\"}})` if offered. In supported Codex desktop chats, the user can also choose **New tab (+) → Desktop** in the right panel. For sign-in or another handoff, have the user select **Take over** and pause your input. After they select **Return control**, inspect the same screen before continuing. Closing the panel leaves the desktop running.\n\n## Open the app in the user’s own browser\n\nIf the user wants the running app on their computer, verify its local port on the Cloud machine. When offered, call `open_cloud_preview` with that port and return its `localUrl`. The URL works only on the user’s computer and the app handles its own login. To share with someone else, use a supported sharing or deployment route for the intended audience.\n\n## If the desktop is unavailable\n\nCheck `capabilities[].remote_desktop` in `cloud_environment.environment_status({})` if the returned `environment_id` matches this desktop. An on-demand desktop can show `enabled: true` and `state: unknown` until first use. The first valid desktop JavaScript call or a viewer connection starts the display. Chrome can start separately when an operation needs a tab.\n\nIf the environment is starting, recheck its tools when ready. If only the viewer works, offer to open it. For a check that another browser can reproduce, try the project’s browser runner or another available browser tool and state what it verified. If the task needs the original tab, native window, or a handoff, report which interaction is blocked, the environment ID, and the missing tool or error.\n\nIf the viewer connects but Chrome fails to start, native windows may still work. If Chrome opens but a site fails to load, compare the same URL with the shell’s configured HTTP client. Report which path failed before proposing a network change.\n"Full snapshot data
{
"description": "Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools.",
"included_files": [],
"name": "cloud-desktop",
"skill_md_contents": "---\nname: cloud-desktop\ndescription: Open an app in shared Chrome, test a user flow, inspect a Linux window, capture the screen, or hand control to the user. Diagnose missing Cloud desktop tools.\n---\n\nUse the attached desktop for hands-on work in a Cloud app, even with the Desktop panel closed. “Try signup and tell me what appears after Submit” or “capture this signed-in tab” calls for the actual browser session. Use the project’s test runner for “run the signup suite.” Use headless automation for repeatable checks such as screenshots at several viewport sizes. If the result depends on a visible window or an existing session, use the browser that reproduces that condition.\n\nFor a broad request like “test signup,” choose the checks that answer the question. If the form shows an error after submission, an API or regression check can help distinguish a display problem from a failed signup. Report what each check established.\n\nUse the browser, tab, or device the user names. If they leave the choice to you, open a Cloud app in shared Chrome at its local URL, such as `http://127.0.0.1:3000`, even when forwarding to the user’s browser is unavailable. For an external URL with no browser specified, follow the available browser tool’s selection instructions.\n\n## Open and inspect\n\nUse the running app if it is ready. To start it, follow the environment’s **Start skill** and its readiness check when available, or use the project’s usual command and verify it responds. When starting an app, avoid managed browser ports such as `8000` and `8085`, even if they appear free. If the app’s port conflicts, use the project’s supported port override and verify the app responds on the new port. For a UI fix, reproduce the problem when possible and repeat those steps after the change. Use the Linux desktop for native windows, file pickers, or flows that cross apps. For example, open an exported PDF to check its layout.\n\nFor the Cloud desktop, follow the first-call instructions on the desktop JavaScript tool offered for this turn (usually `cua_repl.js`). To open a new tab in shared Chrome, use `await cua.createBrowserTab(\"cdp\", url)` when offered. To find an existing tab or app, use `await cua.getState()` and follow the tool’s tab selection or claiming instructions. Use Sky when available for a native window or a screenshot of the whole desktop. Inspect what loaded before reporting success.\n\nIf the user requests a recording, use a recorder that can capture the chosen tab or window. Keep sign-in and credentials out of the footage. Play back the saved video to verify it shows the requested steps, then link the file in this chat.\n\n## Let the user watch or take over\n\nWhen the user asks to see the app or needs to act, open the viewer with `open_in_codex({\"target\":{\"type\":\"cloud-desktop\"}})` if offered. In supported Codex desktop chats, the user can also choose **New tab (+) → Desktop** in the right panel. For sign-in or another handoff, have the user select **Take over** and pause your input. After they select **Return control**, inspect the same screen before continuing. Closing the panel leaves the desktop running.\n\n## Open the app in the user’s own browser\n\nIf the user wants the running app on their computer, verify its local port on the Cloud machine. When offered, call `open_cloud_preview` with that port and return its `localUrl`. The URL works only on the user’s computer and the app handles its own login. To share with someone else, use a supported sharing or deployment route for the intended audience.\n\n## If the desktop is unavailable\n\nCheck `capabilities[].remote_desktop` in `cloud_environment.environment_status({})` if the returned `environment_id` matches this desktop. An on-demand desktop can show `enabled: true` and `state: unknown` until first use. The first valid desktop JavaScript call or a viewer connection starts the display. Chrome can start separately when an operation needs a tab.\n\nIf the environment is starting, recheck its tools when ready. If only the viewer works, offer to open it. For a check that another browser can reproduce, try the project’s browser runner or another available browser tool and state what it verified. If the task needs the original tab, native window, or a handoff, report which interaction is blocked, the environment ID, and the missing tool or error.\n\nIf the viewer connects but Chrome fails to start, native windows may still work. If Chrome opens but a site fails to load, compare the same URL with the shell’s configured HTTP client. Report which path failed before proposing a network change.\n"
}SHA-256 of public snapshot: 777ae12488dcacd630449b5702964a1193dabfa09d008e433904e3422d971eec