Scheduled Tasks In Claude Code Desktop
Use Claude Code Desktop scheduled tasks to run recurring local maintenance: create tasks in Desktop, scope repositories and environments, review autonomous runs, and disable tasks when behavior drifts.
Open the source and read safety notes before installing.
Safety notes
- Scheduled tasks run as autonomous sessions without mid-run approval prompts—scope paths and tools narrowly.
- Tasks inherit Desktop network and connector settings—remove unused MCP connectors.
- Do not schedule destructive maintenance on production branches without explicit policy.
Privacy notes
- Task prompts and run output may include proprietary code and connector payloads.
- Scheduled run logs on shared machines need access controls.
- Disable tasks before offboarding machines that stored local session state.
Prerequisites
- Claude Code Desktop installed with scheduled tasks enabled per plan.
- Repositories and branches the task may touch are identified.
- Human reviewer assigned before merging task-opened changes.
- Rollback plan to disable or delete the task documented.
Schema details
- Install type
- copy
- Reading time
- 8 min
- Difficulty score
- 52
- Troubleshooting
- Yes
- Breaking changes
- No
Full copyable content
Open Claude Code Desktop scheduled tasks, define a self-contained prompt, pick cadence and repo scope, trim connectors, review the first run manually, then enable production schedules only after sign-off.About this resource
TL;DR
Schedule recurring Claude Code maintenance from Desktop with scoped tasks and run review.
Prerequisites & Requirements
- {"task": "Check", "description": "Claude Code Desktop installed with scheduled tasks enabled per plan."}
- {"task": "Check", "description": "Repositories and branches the task may touch are identified."}
- {"task": "Check", "description": "Human reviewer assigned before merging task-opened changes."}
- {"task": "Check", "description": "Rollback plan to disable or delete the task documented."}
Core Concepts Explained
Official docs position Desktop scheduled tasks as recurring Claude Code runs configured from the Desktop app rather than cloud-only routines at claude.ai.
Local cadence vs cloud routines
Desktop scheduled tasks target maintainers who want recurring work tied to Desktop environments; cloud routines use separate triggers documented on code.claude.com.
Autonomous execution
Scheduled runs proceed without mid-run user prompts except permission boundaries already configured—treat schedules like unattended automation.
Step-by-Step Implementation Guide
Define the maintenance goal. Examples: dependency audit, stale branch cleanup, doc link check, or test smoke suite—state success criteria in the prompt.
Open Desktop scheduled tasks. Create a new task with name, prompt, and cadence per Desktop UI (daily, weekly, or custom intervals documented on code.claude.com).
Scope repositories and environment. Limit repos, branches, and network connectors to minimum necessary blast radius.
Pilot one manual run. Inspect diff, logs, and connector actions before enabling the recurring schedule.
Assign a human reviewer. No merge from task output without CODEOWNERS review.
Document rollback. Record steps to disable or delete the task and revert branches if a run misbehaves.
Revisit quarterly. Remove tasks whose prompts no longer match repository layout.
Troubleshooting
Task ran but changed unexpected files
Disable the schedule, revert the branch, and narrow repo path scope in the task configuration before re-enabling.
Connectors accessed production services
Remove unused MCP connectors from the Desktop environment attached to the task.
Cadence too aggressive for quota
Increase interval per Desktop limits and consolidate multiple small tasks into one prompt with a checklist.
Source Verification Notes
Verified against official documentation on 2026-06-16:
- Desktop scheduled tasks documentation describes creating recurring tasks from Claude Code Desktop.
- Tasks combine prompts, repositories, environments, and schedule cadence.
- Runs execute as autonomous Desktop or cloud sessions depending on configuration.
- Teams should review first runs manually before trusting recurring output.
- Tasks can be disabled or edited from Desktop settings when behavior drifts.
Duplicate Check
Complements claude-code-desktop-scheduled-maintenance-capability-pack skill (review matrices) and routines-for-recurring-claude-code-maintenance (cloud routines). This guide focuses on Desktop scheduled task UI workflow.
References
- Primary documentation - https://code.claude.com/docs/en/desktop-scheduled-tasks
Source citations
Add this badge to your README
Show that Scheduled Tasks In Claude Code Desktop is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/guides/scheduled-tasks-in-claude-code-desktop)How it compares
Scheduled Tasks In Claude Code Desktop side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Scheduled Tasks In Claude Code Desktop Use Claude Code Desktop scheduled tasks to run recurring local maintenance: create tasks in Desktop, scope repositories and environments, review autonomous runs, and disable tasks when behavior drifts. Open dossier | Routines For Recurring Claude Code Maintenance Use Claude Code routines for recurring maintenance: schedule triggers, API and GitHub events, scoped connectors, and review of autonomous cloud runs for backlog grooming, docs drift, and deploy verification. Open dossier | Claude Code Subagents For Repository Maintenance Delegate repository maintenance to Claude Code subagents: docs drift scans, dependency report triage, README sync checks, and stale issue grooming with scoped tools, read-first policies, and human merge gates. Open dossier | Auto Mode Hard-Deny Policies For Safe Automation Configure Claude Code auto mode hard-deny rules that block high-risk actions unconditionally, complement soft-deny prompts and team permission policy. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | guides | guides | guides | guides |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | kiannidev | kiannidev | kiannidev | kiannidev |
| Added | 2026-06-16 | 2026-06-16 | 2026-06-16 | 2026-06-13 |
| Platforms | Claude Code | Claude Code | Claude Code | Claude Code |
| Source repo | — | — | — | — |
| Safety notes | ✓Scheduled tasks run as autonomous sessions without mid-run approval prompts—scope paths and tools narrowly. Tasks inherit Desktop network and connector settings—remove unused MCP connectors. Do not schedule destructive maintenance on production branches without explicit policy. | ✓Routines run as full autonomous cloud sessions with no approval prompts—scope repos, network, and connectors narrowly. Actions through GitHub or connectors appear as your linked identity; treat routine output like your own commits and messages. Enable unrestricted branch pushes only on repositories where pushing to existing branches is explicitly approved. | ✓Maintenance subagents can propose file edits and shell commands—start read-only and add write tools only after review policy exists. Parallel subagents multiply tool calls; cap concurrent maintenance runs on large monorepos to control cost and noise. Dependency upgrade suggestions require human verification against semver, license, and security advisories before merge. | ✓Hard-deny rules block regardless of user intent or allow exceptions—misconfiguration can halt legitimate workflows. Auto mode classifiers can still fail open with evaluation errors; hard deny is not a substitute for branch protection and CI gates. Do not rely on auto mode alone for secrets handling; deny credential reads and outbound bulk transfers explicitly. |
| Privacy notes | ✓Task prompts and run output may include proprietary code and connector payloads. Scheduled run logs on shared machines need access controls. Disable tasks before offboarding machines that stored local session state. | ✓Routine prompts and run transcripts may include proprietary code, issue titles, and connector payloads. API trigger tokens are secrets; store bearer tokens in a secret manager, not in public CI logs. Slack, Linear, or other connector actions may expose internal project metadata to linked workspaces. | ✓Maintenance scans read internal docs, issue titles, dependency manifests, and CI configuration that may describe unreleased features. Subagent transcripts may retain file paths and package names from private forks; avoid pasting customer data into maintenance prompts. External MCP connectors can expose additional metadata—document what each maintenance subagent may read. | ✓Auto mode classifiers evaluate tool names, arguments, and session context that may include file paths and repository metadata. Denial messages and debug logs can retain snippets of blocked commands; restrict log access on shared machines. Managed settings sync may expose rule text to all enrolled clients—avoid embedding internal codenames you do not want widely visible. |
| Prerequisites |
|
|
|
|
| Install | — | — | — | — |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.