Documentation 2026-04-24 18:11 UTC to 2026-04-25 21:10 UTC

6 6 

7> Get more out of Claude Code Desktop: parallel sessions with Git isolation, drag-and-drop pane layout, integrated terminal and file editor, side chats, computer use, Dispatch sessions from your phone, visual diff review, app previews, PR monitoring, connectors, and enterprise configuration.7> Get more out of Claude Code Desktop: parallel sessions with Git isolation, drag-and-drop pane layout, integrated terminal and file editor, side chats, computer use, Dispatch sessions from your phone, visual diff review, app previews, PR monitoring, connectors, and enterprise configuration.

8 8 

9The Code tab within the Claude Desktop app lets you use Claude Code through a graphical interface instead of the terminal.9The Claude Desktop app has three tabs: **Chat** for conversations, **Cowork** for [Dispatch and longer agentic work](https://claude.com/product/cowork), and **Code** for software development. This page is the reference for the Code tab.

10 10 

11<CardGroup cols={2}>11<CardGroup cols={2}>

12 <Card title="Download for macOS" icon="apple" href="https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code&utm_medium=docs">12 <Card title="Download for macOS" icon="apple" href="https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code&utm_medium=docs">

20 20 

21For Windows ARM64, download the [ARM64 installer](https://claude.ai/api/desktop/win32/arm64/setup/latest/redirect?utm_source=claude_code\&utm_medium=docs). Linux is not supported.21For Windows ARM64, download the [ARM64 installer](https://claude.ai/api/desktop/win32/arm64/setup/latest/redirect?utm_source=claude_code\&utm_medium=docs). Linux is not supported.

22 22 

23After installing, launch Claude, sign in, and click the **Code** tab. See the [Get started guide](/en/desktop-quickstart) for a full walkthrough of your first session.23After installing, launch Claude, sign in, and click the **Code** tab. The first time you open it on Windows, you need [Git for Windows](https://git-scm.com/downloads/win) installed; restart the app after installing it. For a walkthrough of your first session, see the [Get started guide](/en/desktop-quickstart).

24 24 

25Desktop adds these capabilities on top of the standard Claude Code experience:25In the Code tab, each conversation is a **session**: it has its own chat history, project folder, and code changes, independent of any other session. The sidebar lists your sessions and lets you run several in parallel. Within a session you can:

26 26 

27* [Parallel sessions](#work-in-parallel-with-sessions) with automatic Git worktree isolation27* [Review and comment on diffs](#review-changes-with-diff-view), then [watch the resulting PR through CI](#monitor-pull-request-status)

28* [Drag-and-drop layout](#arrange-your-workspace) with an integrated terminal, file editor, and preview pane28* [Preview your running app](#preview-your-app) in an embedded browser while Claude verifies its own changes

29* [Side chats](#ask-a-side-question-without-derailing-the-session) that branch off without affecting the main thread29* [Arrange panes](#arrange-your-workspace) for the chat, diff, preview, terminal, and file editor side by side

30* [Visual diff review](#review-changes-with-diff-view) with inline comments30* Ask a [side question](#ask-a-side-question-without-derailing-the-session) that uses the session's context without derailing it

31* [Live app preview](#preview-your-app) with dev servers, HTML files, and PDFs31* [Connect external tools](#connect-external-tools) like GitHub, Slack, and Linear

32* [Computer use](#let-claude-use-your-computer) to open apps and control your screen on macOS and Windows32* Let Claude [open apps and control your screen](#let-claude-use-your-computer)

33* [GitHub PR monitoring](#monitor-pull-request-status) with auto-fix, auto-merge, and auto-archive33* Run on your machine, in the [cloud](#run-long-running-tasks-remotely), or over [SSH](#ssh-sessions)

34* [Dispatch](#sessions-from-dispatch) integration: send a task from your phone, get a session here

35* [Scheduled tasks](/en/desktop-scheduled-tasks) that run Claude on a recurring schedule

36* [Connectors](#connect-external-tools) for GitHub, Slack, Linear, and more

37* Local, [SSH](#ssh-sessions), and [cloud](#run-long-running-tasks-remotely) environments

38 34 

39<Note>35For [scheduled recurring work](/en/desktop-scheduled-tasks), [keyboard shortcuts](#keyboard-shortcuts), or [sending tasks from your phone](#sessions-from-dispatch), see the linked pages and sections. If you already use the terminal-based CLI, see the [CLI comparison](#coming-from-the-cli) for what carries over.

40 The workspace layout, terminal, file editor, side chats, and view modes described on this page require Claude Desktop v1.2581.0 or later. Open **Claude → Check for Updates** on macOS or **Help → Check for Updates** on Windows to update.

41</Note>

42 

43This page covers [working with code](#work-with-code), [arranging your workspace](#arrange-your-workspace), [computer use](#let-claude-use-your-computer), [managing sessions](#manage-sessions), [extending Claude Code](#extend-claude-code), and [configuration](#environment-configuration). It also includes a [CLI comparison](#coming-from-the-cli) and [troubleshooting](#troubleshooting).

44 36 

45## Start a session37## Start a session

46 38 

75Permission modes control how much autonomy Claude has during a session: whether it asks before editing files, running commands, or both. You can switch modes at any time using the mode selector next to the send button. Start with Ask permissions to see exactly what Claude does, then move to Auto accept edits or Plan mode as you get comfortable.67Permission modes control how much autonomy Claude has during a session: whether it asks before editing files, running commands, or both. You can switch modes at any time using the mode selector next to the send button. Start with Ask permissions to see exactly what Claude does, then move to Auto accept edits or Plan mode as you get comfortable.

76 68 

77| Mode | Settings key | Behavior |69| Mode | Settings key | Behavior |

78| ---------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |70| ---------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

79| **Ask permissions** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change. Recommended for new users. |71| **Ask permissions** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change. Recommended for new users. |

80| **Auto accept edits** | `acceptEdits` | Claude auto-accepts file edits and common filesystem commands like `mkdir`, `touch`, and `mv`, but still asks before running other terminal commands. Use this when you trust file changes and want faster iteration. |72| **Auto accept edits** | `acceptEdits` | Claude auto-accepts file edits and common filesystem commands like `mkdir`, `touch`, and `mv`, but still asks before running other terminal commands. Use this when you trust file changes and want faster iteration. |

81| **Plan mode** | `plan` | Claude reads files and runs commands to explore, then proposes a plan without editing your source code. Good for complex tasks where you want to review the approach first. |73| **Plan mode** | `plan` | Claude reads files and runs commands to explore, then proposes a plan without editing your source code. Good for complex tasks where you want to review the approach first. |

82| **Auto** | `auto` | Claude executes all actions with background safety checks that verify alignment with your request. Reduces permission prompts while maintaining oversight. Currently a research preview. Available on Max, Team, Enterprise, and API plans. Requires Claude Sonnet 4.6, Opus 4.6, or Opus 4.7 on Team, Enterprise, and API plans; Claude Opus 4.7 only on Max plans. Not available on Pro plans or third-party providers. Enable in your Settings → Claude Code. |74| **Auto** | `auto` | Claude executes all actions with background safety checks that verify alignment with your request. Reduces permission prompts while maintaining oversight. Enable in your Settings → Claude Code. See [availability requirements](#auto-mode-availability) below. |

83| **Bypass permissions** | `bypassPermissions` | Claude runs without any permission prompts, equivalent to `--dangerously-skip-permissions` in the CLI. Enable in your Settings → Claude Code under "Allow bypass permissions mode". Only use this in sandboxed containers or VMs. Enterprise admins can disable this option. |75| **Bypass permissions** | `bypassPermissions` | Claude runs without any permission prompts, equivalent to `--dangerously-skip-permissions` in the CLI. Enable in your Settings → Claude Code under "Allow bypass permissions mode". Only use this in sandboxed containers or VMs. Enterprise admins can disable this option. |

84 76 

85The `dontAsk` permission mode is available only in the [CLI](/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode).77The `dontAsk` permission mode is available only in the [CLI](/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode).

86 78 

79<span id="auto-mode-availability" />

80 

81Auto mode is a research preview available on Max, Team, Enterprise, and API plans. It is not available on Pro plans or third-party providers. On Team, Enterprise, and API plans it requires Claude Sonnet 4.6, Opus 4.6, or Opus 4.7. On Max plans it requires Claude Opus 4.7.

82 

87<Tip title="Best practice">83<Tip title="Best practice">

88 Start complex tasks in Plan mode so Claude maps out an approach before making changes. Once you approve the plan, switch to Auto accept edits or Ask permissions to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.84 Start complex tasks in Plan mode so Claude maps out an approach before making changes. Once you approve the plan, switch to Auto accept edits or Ask permissions to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.

89</Tip>85</Tip>

96 92 

97Claude can start a dev server and open an embedded browser to verify its changes. This works for frontend web apps as well as backend servers: Claude can test API endpoints, view server logs, and iterate on issues it finds. In most cases, Claude starts the server automatically after editing project files. You can also ask Claude to preview at any time. By default, Claude [auto-verifies](#auto-verify-changes) changes after every edit.93Claude can start a dev server and open an embedded browser to verify its changes. This works for frontend web apps as well as backend servers: Claude can test API endpoints, view server logs, and iterate on issues it finds. In most cases, Claude starts the server automatically after editing project files. You can also ask Claude to preview at any time. By default, Claude [auto-verifies](#auto-verify-changes) changes after every edit.

98 94 

99The preview pane can also open static HTML files, PDFs, and images from your project. Click an HTML, PDF, or image path in the chat to open it in preview.95The preview pane can also open static HTML files, PDFs, images, and videos from your project. Click an HTML, PDF, image, or video path in the chat to open it in preview.

100 96 

101From the preview pane, you can:97From the preview pane, you can:

102 98 

144 140 

145## Arrange your workspace141## Arrange your workspace

146 142 

147The desktop app is built around panes you can arrange in any layout: chat, diff, preview, terminal, file, plan, tasks, and subagent. Drag a pane by its header to reposition it, or drag a pane edge to resize it. Press **Cmd+\\** on macOS or **Ctrl+\\** on Windows to close the focused pane. Open additional panes from the **Views** menu in the session toolbar.143The Code tab is built around panes you can arrange in any layout: chat, diff, preview, terminal, file, plan, tasks, and subagent. Drag a pane by its header to reposition it, or drag a pane edge to resize it. Press **Cmd+\\** on macOS or **Ctrl+\\** on Windows to close the focused pane. Open additional panes from the **Views** menu in the session toolbar.

144 

145<Note>

146 The pane layout, terminal, file editor, and view modes in this section require Claude Desktop v1.2581.0 or later. Open **Claude → Check for Updates** on macOS or **Help → Check for Updates** on Windows to update.

147</Note>

148 148 

149### Run commands in the terminal149### Run commands in the terminal

150 150 

152 152 

153### Open and edit files153### Open and edit files

154 154 

155Click a file path in the chat or diff viewer to open it in the file pane. HTML, PDF, and image paths open in the [preview pane](#preview-your-app) instead. Make spot edits and click **Save** to write them back. If the file changed on disk since you opened it, the pane warns you and lets you override or discard. Click **Discard** to revert your edits, or click the path in the pane header to copy the absolute path.155Click a file path in the chat or diff viewer to open it in the file pane. HTML, PDF, image, and video paths open in the [preview pane](#preview-your-app) instead. Make spot edits and click **Save** to write them back. If the file changed on disk since you opened it, the pane warns you and lets you override or discard. Click **Discard** to revert your edits, or click the path in the pane header to copy the absolute path.

156 156 

157The file pane is available in local and SSH sessions. For remote sessions, ask Claude to make the change.157The file pane is available in local and SSH sessions. For remote sessions, ask Claude to make the change.

158 158 

289To include gitignored files like `.env` in new worktrees, create a [`.worktreeinclude` file](/en/common-workflows#copy-gitignored-files-to-worktrees) in your project root.289To include gitignored files like `.env` in new worktrees, create a [`.worktreeinclude` file](/en/common-workflows#copy-gitignored-files-to-worktrees) in your project root.

290 290 

291<Note>291<Note>

292 Session isolation requires [Git](https://git-scm.com/downloads). Most Macs include Git by default. Run `git --version` in Terminal to check. On Windows, Git is required for the Code tab to work: [download Git for Windows](https://git-scm.com/downloads/win), install it, and restart the app. If you run into Git errors, try a Cowork session to help troubleshoot your setup.292 Session isolation requires [Git](https://git-scm.com/downloads). Most Macs include Git by default. Run `git --version` in Terminal to check. On Windows, Git is required for the Code tab to work: [download Git for Windows](https://git-scm.com/downloads/win), install it, and restart the app. If you run into Git errors, ask Claude in the [Cowork tab](https://claude.com/product/cowork) to help troubleshoot your setup.

293</Note>293</Note>

294 294 

295Use the controls at the top of the sidebar to filter sessions by status, project, or environment, and to group sessions by project. To rename a session, click the session title in the toolbar at the top of the active session. To check context usage, see [Check usage](#check-usage). When context fills up, Claude automatically summarizes the conversation and continues working. You can also type `/compact` to trigger summarization earlier and free up context space. See [the context window](/en/how-claude-code-works#the-context-window) for details on how compaction works.295Use the controls at the top of the sidebar to filter sessions by status, project, or environment, and to group sessions by project. To rename a session, click the session title in the toolbar at the top of the active session. To check context usage, see [Check usage](#check-usage). When context fills up, Claude automatically summarizes the conversation and continues working. You can also type `/compact` to trigger summarization earlier and free up context space. See [the context window](/en/how-claude-code-works#the-context-window) for details on how compaction works.

337 337 

338## Extend Claude Code338## Extend Claude Code

339 339 

340Connect external services, add reusable workflows, customize Claude's behavior, and configure preview servers.340Connect external services, add reusable workflows, customize Claude's behavior, and configure preview servers. To manage connectors, skills, and plugins in one place, click **Customize** in the sidebar.

341 341 

342### Connect external tools342### Connect external tools

343 343 

537 537 

538Once added, the connection appears in the environment dropdown. Select it to start a session on that machine. Claude runs on the remote machine with access to its files and tools.538Once added, the connection appears in the environment dropdown. Select it to start a session on that machine. Claude runs on the remote machine with access to its files and tools.

539 539 

540The remote machine must run Linux or macOS, and Claude Code must be installed on it. Once connected, SSH sessions support permission modes, connectors, plugins, and MCP servers.540The remote machine must run Linux or macOS. Desktop installs Claude Code on the remote machine automatically the first time you connect. Once connected, SSH sessions support permission modes, connectors, plugins, and MCP servers.

541 541 

542#### Pre-configure SSH connections for your team542#### Pre-configure SSH connections for your team

543 543 

586| `autoMode` | customize what the auto mode classifier trusts and blocks across your organization. See [Configure auto mode](/en/auto-mode-config). |586| `autoMode` | customize what the auto mode classifier trusts and blocks across your organization. See [Configure auto mode](/en/auto-mode-config). |

587| `sshConfigs` | pre-configure [SSH connections](#pre-configure-ssh-connections-for-your-team) that appear in the environment dropdown. Users cannot edit or delete managed connections. |587| `sshConfigs` | pre-configure [SSH connections](#pre-configure-ssh-connections-for-your-team) that appear in the environment dropdown. Users cannot edit or delete managed connections. |

588 588 

589`permissions.disableBypassPermissionsMode` and `disableAutoMode` also work in user and project settings, but placing them in managed settings prevents users from overriding them. `autoMode` is read from user settings, `.claude/settings.local.json`, and managed settings, but not from the checked-in `.claude/settings.json`: a cloned repo cannot inject its own classifier rules. For the complete list of managed-only settings including `allowManagedPermissionRulesOnly` and `allowManagedHooksOnly`, see [managed-only settings](/en/permissions#managed-only-settings).589A managed settings file deployed to disk on each machine applies to Desktop sessions. Managed settings pushed remotely through the admin console currently reach CLI and IDE sessions only, so for Desktop deployments either distribute the file via MDM or use the [admin console controls](#admin-console-controls) above.

590 590 

591Remote managed settings uploaded through the admin console currently apply to CLI and IDE sessions only. For Desktop-specific restrictions, use the admin console controls above.591`permissions.disableBypassPermissionsMode` and `disableAutoMode` also work in user and project settings, but placing them in managed settings prevents users from overriding them. `autoMode` is read from user settings, `.claude/settings.local.json`, and managed settings, but not from the checked-in `.claude/settings.json`: a cloned repo cannot inject its own classifier rules. For the complete list of managed-only settings including `allowManagedPermissionRulesOnly` and `allowManagedHooksOnly`, see [managed-only settings](/en/permissions#managed-only-settings).

592 592 

593### Device management policies593### Device management policies

594 594 

637| `--permission-mode` | Mode selector next to the send button |637| `--permission-mode` | Mode selector next to the send button |

638| `--dangerously-skip-permissions` | Bypass permissions mode. Enable in Settings → Claude Code → "Allow bypass permissions mode". Enterprise admins can disable this setting. |638| `--dangerously-skip-permissions` | Bypass permissions mode. Enable in Settings → Claude Code → "Allow bypass permissions mode". Enterprise admins can disable this setting. |

639| `--add-dir` | Add multiple repos with the **+** button in remote sessions |639| `--add-dir` | Add multiple repos with the **+** button in remote sessions |

640| `--allowedTools`, `--disallowedTools` | Not available in Desktop |640| `--allowedTools`, `--disallowedTools` | No per-session equivalent. Permission rules in [settings files](/en/settings) still apply. |

641| `--verbose` | [Verbose view mode](#switch-view-modes) in the Transcript view dropdown |641| `--verbose` | [Verbose view mode](#switch-view-modes) in the Transcript view dropdown |

642| `--print`, `--output-format` | Not available. Desktop is interactive only. |642| `--print`, `--output-format` | Not available. Desktop is interactive only. |

643| `ANTHROPIC_MODEL` env var | Model dropdown next to the send button |643| `ANTHROPIC_MODEL` env var | Model dropdown next to the send button |

63 You can also select:63 You can also select:

64 64 

65 * **Remote**: Run sessions on Anthropic's cloud infrastructure that continue even if you close the app. Remote sessions use the same infrastructure as [Claude Code on the web](/en/claude-code-on-the-web).65 * **Remote**: Run sessions on Anthropic's cloud infrastructure that continue even if you close the app. Remote sessions use the same infrastructure as [Claude Code on the web](/en/claude-code-on-the-web).

66 * **SSH**: Connect to a remote machine over SSH (your own servers, cloud VMs, or dev containers). Claude Code must be installed on the remote machine.66 * **SSH**: Connect to a remote machine over SSH, such as your own servers, cloud VMs, or dev containers. Desktop installs Claude Code on the remote machine automatically the first time you connect.

67 </Step>67 </Step>

68 68 

69 <Step title="Choose a model">69 <Step title="Choose a model">

6 6 

7> Set up scheduled tasks in Claude Code Desktop to run Claude automatically on a recurring basis for daily code reviews, dependency audits, or morning briefings.7> Set up scheduled tasks in Claude Code Desktop to run Claude automatically on a recurring basis for daily code reviews, dependency audits, or morning briefings.

8 8 

9By default, scheduled tasks start a new session automatically at a time and frequency you choose. Use them for recurring work like daily code reviews, dependency update checks, or morning briefings that pull from your calendar and inbox.9Scheduled tasks start a new session automatically at a time and frequency you choose. Use them for recurring work like daily code reviews, dependency update checks, or morning briefings that pull from your calendar and inbox.

10 

11The Desktop app's **Routines** page lets you create both local scheduled tasks and remote [routines](/en/routines). A local task runs on your machine with direct access to your files and tools, but only fires while the app is open and your computer is awake. A remote routine runs on Anthropic-managed cloud infrastructure even when your computer is off, and can also fire on API calls or GitHub events. This page covers local scheduled tasks; for remote routines and their trigger options, see [Routines](/en/routines).

10 12 

11## Compare scheduling options13## Compare scheduling options

12 14 

28 Use **cloud tasks** for work that should run reliably without your machine. Use **Desktop tasks** when you need access to local files and tools. Use **`/loop`** for quick polling during a session.30 Use **cloud tasks** for work that should run reliably without your machine. Use **Desktop tasks** when you need access to local files and tools. Use **`/loop`** for quick polling during a session.

29</Tip>31</Tip>

30 32 

31The Schedule page supports two kinds of tasks:

32 

33* **Local tasks**: run on your machine. They have direct access to your local files and tools, but the desktop app must be open and your computer awake for them to run.

34* **Remote tasks**: run on Anthropic-managed cloud infrastructure. They keep running even when your computer is off, but work against a fresh clone of your repository rather than your local checkout.

35 

36Both kinds appear in the same task grid. Click **New task** to pick which kind to create. The rest of this page covers local tasks; for remote tasks, see [Routines](/en/routines).

37 

38See [How scheduled tasks run](#how-scheduled-tasks-run) for details on missed runs and catch-up behavior for local tasks.

39 

40<Note>33<Note>

41 By default, local scheduled tasks run against whatever state your working directory is in, including uncommitted changes. Enable the worktree toggle in the prompt input to give each run its own isolated Git worktree, the same way [parallel sessions](/en/desktop#work-in-parallel-with-sessions) work.34 By default, scheduled tasks run against whatever state your working directory is in, including uncommitted changes. Enable the worktree toggle when creating the task to give each run its own isolated Git worktree, the same way [parallel sessions](/en/desktop#work-in-parallel-with-sessions) work.

42</Note>35</Note>

43 36 

44## Create a scheduled task37## Create a scheduled task

45 38 

46To create a local scheduled task, click **Schedule** in the sidebar, click **New task**, and choose **New local task**. Configure these fields:39Click **Routines** in the sidebar, then click **New routine** and choose **Local**. Configure these fields:

47 40 

48| Field | Description |41| Field | Description |

49| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |42| ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

50| Name | Identifier for the task. Converted to lowercase kebab-case and used as the folder name on disk. Must be unique across your tasks. |43| Name | Identifier for the task. Converted to lowercase kebab-case and used as the folder name on disk. Must be unique across your tasks. |

51| Description | Short summary shown in the task list. |44| Description | Short summary shown in the task list. |

52| Prompt | The instructions sent to Claude when the task runs. Write this the same way you'd write any message in the prompt box. The prompt input also includes controls for model, permission mode, working folder, and worktree. |45| Instructions | What Claude should do when the task runs. Write this the same way you'd write any message in the prompt box. The instructions input includes pickers for the permission mode and model, and below it you select the working folder and whether to run in an isolated worktree. |

53| Frequency | How often the task runs. See [frequency options](#frequency-options) below. |46| Schedule | How often the task runs. See [schedule options](#schedule-options) below. |

47 

48A folder is required before you can save the task. If you haven't trusted that folder yet, Desktop prompts you to trust it before saving.

54 49 

55You can also create a task by describing what you want in any session. For example, "set up a daily code review that runs every morning at 9am."50You can also create a task by describing what you want in any session. For example, "set up a daily code review that runs every morning at 9am" creates a recurring task, and "remind me at 3pm tomorrow to check the deploy" creates a one-time task that disables itself after it fires.

56 51 

57## Frequency options52## Schedule options

58 53 

59Pick a preset from the frequency dropdown, or ask Claude for anything the picker doesn't cover:54Pick a preset from the Schedule control:

60 55 

61* **Manual**: no schedule, only runs when you click **Run now**. Useful for saving a prompt you trigger on demand56* **Manual**: no schedule, only runs when you click **Run now**. Useful for saving a prompt you trigger on demand

62* **Hourly**: runs every hour. Each task gets a fixed offset of up to 10 minutes from the top of the hour to stagger API traffic57* **Hourly**: runs every hour

63* **Daily**: shows a time picker, defaults to 9:00 AM local time58* **Daily**: shows a time picker, defaults to 9:00 AM local time

64* **Weekdays**: same as Daily but skips Saturday and Sunday59* **Weekdays**: same as Daily but skips Saturday and Sunday

65* **Weekly**: shows a time picker and a day picker60* **Weekly**: shows a time picker and a day picker

66 61 

67For intervals the picker doesn't offer (every 15 minutes, first of each month, etc.), ask Claude in any Desktop session to set the schedule. Use plain language; for example, "schedule a task to run all the tests every 6 hours."62For intervals the picker doesn't offer, such as every 15 minutes, the first of each month, or a single run at a specific future time, ask Claude in any Desktop session to set the schedule. Use plain language; for example, "schedule a task to run all the tests every 6 hours."

68 63 

69## How scheduled tasks run64## How scheduled tasks run

70 65 

71Local scheduled tasks run on your machine. Desktop checks the schedule every minute while the app is open and starts a fresh session when a task is due, independent of any manual sessions you have open. Each task gets a fixed delay of up to 10 minutes after the scheduled time to stagger API traffic. The delay is deterministic: the same task always starts at the same offset.66Scheduled tasks run on your machine. Desktop checks the schedule every minute while the app is open and starts a fresh session when a task is due, independent of any manual sessions you have open. Each task gets a small delay of a few minutes after the scheduled time to stagger API traffic. The delay is deterministic: the same task always starts at the same offset.

72 67 

73When a task fires, you get a desktop notification and a new session appears under a **Scheduled** section in the sidebar. Open it to see what Claude did, review changes, or respond to permission prompts. The session works like any other: Claude can edit files, run commands, create commits, and open pull requests.68When a task fires, you get a desktop notification and a new session appears under a **Scheduled** section in the sidebar. Open it to see what Claude did, review changes, or respond to permission prompts. The session works like any other: Claude can edit files, run commands, create commits, and open pull requests.

74 69 

75Tasks only run while the desktop app is running and your computer is awake. If your computer sleeps through a scheduled time, the run is skipped. To prevent idle-sleep, enable **Keep computer awake** in Settings under **Desktop app → General**. Closing the laptop lid still puts it to sleep. For tasks that need to run even when your computer is off, or that should trigger automatically on an API call or GitHub event, use a [routine](/en/routines) instead.70Tasks only run while the desktop app is running and your computer is awake. If your computer sleeps through a scheduled time, the run is skipped. To prevent idle-sleep, enable **Keep computer awake** in Settings under **Desktop app → General**. Closing the laptop lid still puts it to sleep. For tasks that need to run even when your computer is off, or that should trigger on an API call or GitHub event, create a remote [routine](/en/routines) instead.

76 71 

77## Missed runs72## Missed runs

78 73 

88 83 

89## Manage scheduled tasks84## Manage scheduled tasks

90 85 

91Click a task in the **Schedule** list to open its detail page. From here you can:86Click a task in the **Routines** list to open its detail page. From here you can:

92 87 

93* **Run now**: start the task immediately without waiting for the next scheduled time88* **Run now**: start the task immediately without waiting for the next scheduled time

94* **Toggle repeats**: pause or resume scheduled runs without deleting the task89* **Status**: toggle between Active and Paused to pause or resume scheduled runs without deleting the task

95* **Edit**: change the prompt, frequency, folder, or other settings90* **Edit**: change the instructions, schedule, folder, or other settings

96* **Review history**: see every past run, including ones that were skipped because your computer was asleep91* **Review history**: see every past run, including skipped runs. Hover a skipped entry to see why: your computer was asleep, the previous run was still in progress, or other scheduled tasks were already running. Click **Show more** to load older entries.

97* **Review allowed permissions**: see and revoke saved tool approvals for this task from the **Always allowed** panel92* **Review allowed permissions**: see and revoke saved tool approvals for this task from the **Always allowed** panel

98* **Delete**: remove the task and archive all sessions it created93* **Delete**: remove the task and archive all sessions it created

99 94 

100You can also manage tasks by asking Claude in any Desktop session. For example, "pause my dependency-audit task", "delete the standup-prep task", or "show me my scheduled tasks."95You can also list, create, edit, and pause tasks by asking Claude in any Desktop session. For example, "pause my dependency-audit task" or "show me my scheduled tasks." To delete a task, use the **Delete** button on its detail page.

101 96 

102To edit a task's prompt on disk, open `~/.claude/scheduled-tasks/<task-name>/SKILL.md` (or under [`CLAUDE_CONFIG_DIR`](/en/env-vars) if set). The file uses YAML frontmatter for `name` and `description`, with the prompt as the body. Changes take effect on the next run. Schedule, folder, model, and enabled state are not in this file: change them through the Edit form or ask Claude.97To edit a task's prompt on disk, open `~/.claude/scheduled-tasks/<task-name>/SKILL.md` (or under [`CLAUDE_CONFIG_DIR`](/en/env-vars) if set). The file uses YAML frontmatter for `name` and `description`, with the prompt as the body. Changes take effect on the next run. Schedule, folder, model, and enabled state are not in this file: change them through the Edit form or ask Claude.

103 98 

44 44 

45## Create a routine45## Create a routine

46 46 

47Create a routine from the web, the Desktop app, or the CLI. All three surfaces write to the same cloud account, so a routine you create in the CLI shows up at claude.ai/code/routines immediately. In the Desktop app, click **New task** and choose **New remote task**; choosing **New local task** instead creates a [local Desktop scheduled task](/en/desktop-scheduled-tasks), which runs on your machine and is not a routine.47Create a routine from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud account, so a routine you create in one shows up in the others immediately. In the Desktop app, click **Routines** in the sidebar, then **New routine**, and choose **Remote**; choosing **Local** instead creates a [Desktop scheduled task](/en/desktop-scheduled-tasks), which runs on your machine rather than in the cloud.

48 48 

49The creation form sets up the routine's prompt, repositories, environment, connectors, and triggers.49The creation form sets up the routine's prompt, repositories, environment, connectors, and triggers.

50 50 

66 </Step>66 </Step>

67 67 

68 <Step title="Select repositories">68 <Step title="Select repositories">

69 Add one or more GitHub repositories for Claude to work in. Each repository is cloned at the start of a run, starting from the default branch. Claude creates `claude/`-prefixed branches for its changes. To allow pushes to any branch, enable **Allow unrestricted branch pushes** for that repository.69 Add one or more GitHub repositories for Claude to work in. Each repository is cloned at the start of a run, starting from the default branch. Claude creates `claude/`-prefixed branches for its changes.

70 </Step>70 </Step>

71 71 

72 <Step title="Select an environment">72 <Step title="Select an environment">

97 </Tabs>97 </Tabs>

98 </Step>98 </Step>

99 99 

100 <Step title="Review connectors">100 <Step title="Review connectors and permissions">

101 All of your connected [MCP connectors](/en/mcp) are included by default. Remove any that the routine doesn't need. Connectors give Claude access to external services like Slack, Linear, or Google Drive during each run.101 The **Connectors** and **Permissions** tabs at the bottom of the form control what the routine can reach.

102 

103 Under Connectors, all of your connected [MCP connectors](/en/mcp) are included by default. Remove any the routine doesn't need. Claude can use every tool from an included connector, including writes, without asking for permission during a run.

104 

105 Under Permissions, enable **Allow unrestricted branch pushes** for any repository where Claude should be able to push to existing branches instead of only `claude/`-prefixed ones.

102 </Step>106 </Step>

103 107 

104 <Step title="Create the routine">108 <Step title="Create the routine">

116 120 

117The CLI also supports managing existing routines. Run `/schedule list` to see all routines, `/schedule update` to change one, or `/schedule run` to trigger it immediately.121The CLI also supports managing existing routines. Run `/schedule list` to see all routines, `/schedule update` to change one, or `/schedule run` to trigger it immediately.

118 122 

119### Create from the Desktop app

120 

121Open the **Schedule** page in the Desktop app, click **New task**, and choose **New remote task**. The Desktop app shows both local scheduled tasks and routines in the same grid. See [Desktop scheduled tasks](/en/desktop-scheduled-tasks) for details on the local option.

122 

123## Configure triggers123## Configure triggers

124 124 

125A routine starts when one of its triggers matches. You can attach any combination of schedule, API, and GitHub triggers to the same routine, and add or remove them at any time from the **Select a trigger** section of the routine's edit form.125A routine starts when one of its triggers matches. You can attach any combination of schedule, API, and GitHub triggers to the same routine, and add or remove them at any time from the **Select a trigger** section of the routine's edit form.

145 145 

146Claude Code watches `~/.claude/themes/` and reloads when a file changes, so edits made in your editor apply to a running session without a restart.146Claude Code watches `~/.claude/themes/` and reloads when a file changes, so edits made in your editor apply to a running session without a restart.

147 147 

148Below is the full list of customizations you can set in `overrides`. The interactive editor in `/theme` shows the same tokens with a live preview, including a small number of internal tokens not covered here.

149 

150<Accordion title="Color token reference">

151 The following example combines tokens from several of the groups below: the brand accent, the plan mode border, the diff backgrounds, and the fullscreen message background.

152 

153 ```json ~/.claude/themes/midnight.json theme={null}

154 {

155 "name": "Midnight",

156 "base": "dark",

157 "overrides": {

158 "claude": "#a78bfa",

159 "planMode": "#38bdf8",

160 "diffAdded": "#14532d",

161 "diffRemoved": "#7f1d1d",

162 "userMessageBackground": "#1e1b4b"

163 }

164 }

165 ```

166 

167 #### Text and accent colors

168 

169 Control the primary brand accent and the foreground text shades used throughout the interface.

170 

171 | Token | Controls |

172 | :------------ | :--------------------------------------------------------------- |

173 | `claude` | Primary brand accent, used for the spinner and assistant label |

174 | `text` | Default foreground text |

175 | `inverseText` | Text drawn on top of a colored background, such as status badges |

176 | `inactive` | Secondary text such as hints, timestamps, and disabled items |

177 | `subtle` | Faint borders and de-emphasized secondary text |

178 | `permission` | Dialog borders, including permission prompts and pickers |

179 | `remember` | Memory and `CLAUDE.md` indicators |

180 

181 #### Status colors

182 

183 Signal success, failure, and warning states across messages and indicators.

184 

185 | Token | Controls |

186 | :-------- | :--------------------------------------------------- |

187 | `success` | Success messages and passing checks |

188 | `error` | Error messages and failures |

189 | `warning` | Warnings, caution messages, and the auto mode border |

190 | `merged` | Merged pull request status |

191 

192 #### Input box and mode indicators

193 

194 Set the input box border color and the accent shown while a permission mode or indicator is active.

195 

196 | Token | Controls |

197 | :------------- | :------------------------------------------------- |

198 | `promptBorder` | Input box border in the default permission mode |

199 | `planMode` | Plan mode accent and border |

200 | `autoAccept` | Accept-edits mode accent and border |

201 | `bashBorder` | Input box border when entering a `!` shell command |

202 | `ide` | IDE connection indicator |

203 | `fastMode` | Fast mode indicator |

204 

205 #### Diff rendering

206 

207 Color added and removed code in file edits and reviews.

208 

209 | Token | Controls |

210 | :------------------ | :------------------------------------------------- |

211 | `diffAdded` | Background of added lines |

212 | `diffRemoved` | Background of removed lines |

213 | `diffAddedDimmed` | Background of unchanged context near added lines |

214 | `diffRemovedDimmed` | Background of unchanged context near removed lines |

215 | `diffAddedWord` | Word-level highlight within an added line |

216 | `diffRemovedWord` | Word-level highlight within a removed line |

217 

218 #### Fullscreen mode

219 

220 Apply only in [fullscreen rendering mode](/en/fullscreen), where messages have a background fill.

221 

222 | Token | Controls |

223 | :---------------------- | :------------------------------------------------ |

224 | `userMessageBackground` | Background behind your messages in the transcript |

225 | `selectionBg` | Background of text selected with the mouse |

226 

227 #### Shimmer variants and subagent colors

228 

229 Several tokens have a paired `Shimmer` variant, such as `claudeShimmer` and `warningShimmer`, that supplies the lighter color used in the spinner's animated gradient. Override the shimmer alongside its base token if the animation looks mismatched.

230 

231 Each [subagent](/en/sub-agents) and parallel task is shown in one of eight named colors so you can tell them apart in the transcript. The token names follow the pattern `<color>_FOR_SUBAGENTS_ONLY`, where `<color>` is `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan`. Override these to change what each named color looks like. For example, a subagent with `color: blue` in its definition is drawn using the `blue_FOR_SUBAGENTS_ONLY` value.

232</Accordion>

233 

148## Switch to fullscreen rendering234## Switch to fullscreen rendering

149 235 

150If the display flickers or the scroll position jumps while Claude is working, switch to [fullscreen rendering mode](/en/fullscreen). It draws to a separate screen the terminal reserves for full-screen apps instead of appending to your normal scrollback, which keeps memory usage flat and adds mouse support for scrolling and selection. In this mode you scroll with the mouse or PageUp inside Claude Code rather than with your terminal's native scrollback; see the [fullscreen page](/en/fullscreen#search-and-review-the-conversation) for how to search and copy.236If the display flickers or the scroll position jumps while Claude is working, switch to [fullscreen rendering mode](/en/fullscreen). It draws to a separate screen the terminal reserves for full-screen apps instead of appending to your normal scrollback, which keeps memory usage flat and adds mouse support for scrolling and selection. In this mode you scroll with the mouse or PageUp inside Claude Code rather than with your terminal's native scrollback; see the [fullscreen page](/en/fullscreen#search-and-review-the-conversation) for how to search and copy.