Claude scheduled tasks: choose the right place to run.
Use /loop for short-lived polling in Claude Code, a local Desktop task for recurring work on your files, or a cloud routine for work that must run with your laptop off. The right choice depends on access, persistence and what each run needs to decide.
This guide covers Claude Code scheduling, not every Claude product surface. Whenever is a separate workflow platform, not a settings screen for Claude.
Three modes. Three different operating contracts.
Current official documentation, reviewed September 24, 2026. Routines are in research preview; check the linked docs for changing limits and availability.
CLI /loop
In the current conversation
Best for checking a build, watching a deployment or revisiting a PR while a Claude Code session is running.
Where it runs
Claude Code must be running and idle for a task to fire. Local files and tools come from the session.
What persists
CronCreate tasks restore on --resume or --continue unless expired or overdue one-shots. Self-paced loops do not restore. A new conversation clears session tasks.
Timing & limits
Fixed schedules have one-minute granularity and recurring tasks expire after seven days. A busy session runs a due task once when idle, not once for every missed interval.
Best for recurring or event-driven Claude Code work using selected repositories, an environment and connectors.
Where it runs
Runs on Anthropic-managed infrastructure by default, or an organization’s configured self-hosted environment. No running laptop session is needed.
What persists
The configuration persists in your account. Runs use fresh repository clones, not your laptop’s uncommitted files.
Timing & limits
Recurring schedules have a one-hour minimum and may start a few minutes late. API and GitHub triggers are also supported. Subscription usage and account limits still apply.
Start with a read-only task. Observe a real run before granting write access or leaving it unattended.
01
Poll in the CLI
/loop 5m check whether the deployment finished and report its status; do not change anything
Open Claude Code in the relevant project and verify the tools it needs are available.
Use an explicit interval for a fixed schedule; a prompt without an interval lets Claude choose the delay.
Ask “what scheduled tasks do I have?” to confirm it, and “cancel the deploy check job” when finished. Do not treat this as a durable service.
02
Schedule a local Desktop task
Code → Routines → New routine → Local
Choose a name, instructions, working folder, model, permission mode and schedule. Use an isolated worktree if the task should not work on your current uncommitted changes.
Choose Run now. Review output and grant only the permissions this task needs; interaction-required tools can still block later runs.
Keep the app open and the computer awake. Write prompts that tolerate a late catch-up run. Pausing the task preserves its configuration.
03
Create a cloud routine
/schedule daily PR review at 9am
Use the routines web page, Desktop’s Cloud option or /schedule in a CLI signed in with an eligible claude.ai subscription. A Console API-key login is not the same thing.
Set a self-contained prompt, repositories, environment and trigger. Review the connectors: currently all connected connectors are included by default, so remove the ones this routine does not need.
Run now, open the session transcript and inspect what actually happened. Check network access, outputs, account limits and write permissions before relying on the schedule.
Claude’s routine docs say a green status means the session started and exited without an infrastructure error, not that the task succeeded. Read the transcript and verify the result.
Scope the authority
A routine can run shell commands and use included connectors, including writes, generally without pausing for approval. Limit repositories, network access and connectors to the job; some artifact actions still require approval.
Plan for timing and usage limits
These are not exact-second schedulers. Routines consume subscription usage and have an account-level daily run cap. Usage credits can permit metered overage; one-off runs are exempt from the daily cap, not from subscription usage.
Treat repeat actions as a design problem
Before posting messages or creating records, decide how the task identifies work it already processed. A schedule alone does not guarantee exactly-once external side effects.
When the work has settled into a process.
Claude routines already offer cloud scheduling. Choose Whenever for a different reason: when you want the recurring business process expressed as a typed workflow with explicit triggers, branches and integration calls, not a new open-ended instruction on each run.
For example: read yesterday’s onboarding rows, validate required fields, group blocked accounts by owner, then post one Slack summary. Those steps can be explicit code. Add AI only if one step needs classification or drafting.
BriefDescribe the rule
Name inputs, exceptions and the destination.
WorkflowInspect the logic
Keep branches and AI boundaries explicit.
TestCheck real inputs
Include missing data and repeat delivery.
PublishRun on a trigger
Review outputs and own the exceptions.
A separate path for recurring business workflows, not a replacement Claude scheduling interface.
Describe the process and Whenever’s AI writes the workflow, or point your coding agent at Whenever’s MCP server and have it build, test and deploy the workflow for you. This is not an automatic import of a Claude routine. Connections, permissions and runtime-specific behavior need review.
A few useful answers
Can Claude scheduled tasks run when my laptop is off?
Cloud routines can: they run on Anthropic-managed infrastructure by default, or a configured organization self-hosted environment. Local Desktop tasks need the app open and computer awake. CLI scheduled tasks need a running Claude Code session.
Does /loop survive a restart?
Some scheduled tasks restore when you resume the same conversation with --resume or --continue. Expired recurring tasks and overdue one-shot tasks do not; self-paced loops, background Bash and monitor tasks are not restored. Starting a new conversation clears session-scoped tasks.
What happens if a Desktop task misses its schedule?
On app startup or wake, Desktop checks the last seven days and starts one catch-up run for the most recently missed time. It does not replay every missed interval. The task may run much later than intended, so time-sensitive instructions need a guard.
Why can’t I run a cloud routine every five minutes?
The documented minimum recurring interval for cloud routines is one hour. CLI and Desktop scheduling have one-minute minimum granularity, but require the relevant local runtime to remain available. Choose the mode for its full operating constraints, not the interval alone.
When would I use Whenever instead of a Claude routine?
Use a Claude routine when you want Claude to carry out a recurring, repository-aware or investigative task. Consider Whenever when the business process has known steps you want represented as a typed workflow, with bounded AI only where it helps. Both can run without your laptop; the distinction is the execution contract, not a blanket cloud advantage.
