Tasks are session-scoped. When you resume with
--resume or --continue, Claude Code restores tasks that haven’t expired, except those listed under Limitations. For scheduling that survives independently of any session, create a cloud scheduled task, set up a Desktop scheduled task, or use GitHub Actions.
Compare scheduling options
Claude Code offers three ways to schedule recurring or one-off work:Run a prompt repeatedly with /loop
The/loop bundled skill is the quickest way to run a prompt on repeat while the session stays open. Both the interval and the prompt are optional, and what you provide determines how the loop behaves.
You can also pass a skill as the prompt, for example
/loop 20m /review-pr 1234, to re-run that skill each iteration. A scheduled fire only runs skills that Claude is allowed to invoke on its own. The following reach Claude as plain text instead of executing:
- Built-in commands such as
/permissions,/model, or/clear - Skills marked
disable-model-invocation: true, including the bundled/verifyskill - Skills withheld from Claude by a
skillOverridessetting or aSkilldeny rule - MCP prompts such as
/mcp__github__list_prs
Run on a fixed interval
When you supply an interval, Claude converts it to a cron expression, schedules the job, and confirms the cadence and job ID.30m, or trail it as a clause like every 2 hours. Supported units are s for seconds, m for minutes, h for hours, and d for days.
Seconds are rounded up to the nearest minute since cron has one-minute granularity. Intervals that don’t map to a clean cron step, such as 7m or 90m, are rounded to the nearest interval that does and Claude tells you what it picked.
Let Claude choose the interval
When you omit the interval, Claude chooses one dynamically instead of running on a fixed cron schedule. After each iteration it picks a delay between one minute and one hour based on what it observed: short waits while a build is finishing or a PR is active, longer waits when nothing is pending. The chosen delay and the reason for it are printed at the end of each iteration. The example below checks CI and review comments, with Claude waiting longer between iterations once the PR goes quiet:/loop schedule. Monitor runs a background script and streams each output line back, which avoids polling altogether and is often more token-efficient and responsive than re-running a prompt on an interval.
A dynamically scheduled loop appears in your scheduled task list like any other task, so you can list or cancel it the same way. The list shows its pending wakeup as a one-shot task, so a wakeup scheduled for :00 or :30 can run a little early. The seven-day expiry applies to the loop too.
Dynamically chosen intervals and the built-in maintenance prompt work on every provider, and with feature-flag fetching turned off. On Amazon Bedrock, Claude Platform on AWS, Google Cloud’s Agent Platform, and Microsoft Foundry, or with fetching turned off, both require Claude Code v2.1.248 or later.
Run the built-in maintenance prompt
When you omit the prompt, Claude uses a built-in maintenance prompt instead of one you supply. On each iteration it works through the following, in order:- continue any unfinished work from the conversation
- tend to the current branch’s pull request: review comments, failed CI runs, merge conflicts
- run cleanup passes such as bug hunts or simplification when nothing else is pending
/loop runs this prompt at a dynamically chosen interval. Add an interval, for example /loop 15m, to run it on a fixed schedule instead. To replace the built-in prompt with your own default, see Customize the default prompt with loop.md.
Customize the default prompt with loop.md
Create aloop.md file to replace the built-in maintenance prompt with your own instructions. It defines a single default prompt for bare /loop, not a list of separate scheduled tasks, and Claude Code ignores it whenever you supply a prompt on the command line. To schedule additional prompts alongside it, use /loop <prompt> or ask Claude directly.
Claude looks for the file in two locations and uses the first one it finds.
The file is plain Markdown with no required structure. Write it as if you were typing the
/loop prompt directly. The following example keeps a release branch healthy:
.claude/loop.md
loop.md take effect on the next iteration, so you can refine the instructions while a loop is running. When no loop.md exists in either location, the loop falls back to the built-in maintenance prompt. Keep the file concise: content beyond 25,000 bytes is truncated.
Stop a loop
To stop a self-paced/loop while it is waiting for the next iteration, press Esc. This clears the pending wakeup so the loop does not fire again. Tasks you scheduled by asking Claude directly are not affected by Esc and stay in place until you delete them.
In self-paced mode, Claude can also end the loop on its own once the task is complete. Claude calls the ScheduleWakeup tool with stop: true, which cancels the pending wakeup immediately. If an iteration ends without either rescheduling or stopping, Claude Code schedules one fallback wakeup about 20 minutes later and ends the loop when that iteration doesn’t reschedule either.
Loops on a fixed interval keep running until you cancel them like any other scheduled task or seven days elapse.
Set a one-time reminder
For one-shot reminders, describe what you want in natural language instead of using/loop. Claude schedules a single-fire task that deletes itself after running.
Manage session-scoped scheduled tasks
Ask Claude in natural language to list or cancel tasks, or reference the underlying tools directly.
Each scheduled task has an 8-character ID you can pass to
CronDelete. A session can hold up to 50 scheduled tasks at once.
How session-scoped scheduled tasks run
The scheduler checks every second for due tasks and enqueues them at low priority. A scheduled prompt fires between your turns, not while Claude is mid-response. If Claude is busy when a task comes due, the prompt waits until the current turn ends. All times are interpreted in your local timezone. A cron expression like0 9 * * * means 9am wherever you’re running Claude Code, not UTC.
Jitter
A scheduled task can run at a different time than its schedule says. If every session’s tasks ran exactly on schedule, many of them would call the API at the same moment, so Claude Code shifts each task’s run time. Recurring tasks run late, except a task that runs every five minutes, written*/5 * * * *. One-shot tasks scheduled on the hour or half hour run a little early.
To see when a task is next due, read the row under Claude’s CronCreate call in your terminal. The row shows that time after the schedule, for example next run 10:21 AM. To check again later, ask Claude to list your tasks and look for next run in the rows under the CronList call. Next run times in these rows require Claude Code v2.1.299 or later.
How late a recurring task runs
Unless it runs every five minutes, a recurring task starts each run late by up to half the gap to the next run, and by at most 30 minutes. Your task is one of these three cases:- Evenly spaced runs: a task with equal gaps, such as hourly, daily, or every 10 minutes, runs the same number of minutes late every time, including when the session is idle.
- Unevenly spaced runs: a task with uneven gaps, such as one scheduled for
:00and:15each hour, can run a different number of minutes late at each. - Every five minutes: a task written
*/5 * * * *isn’t delayed. A run exactly five minutes after the last one would start after a five-minute prompt cache had expired, so each run starts 15 seconds sooner.
For example,
7,37 * * * * schedules a task for :07 and :37, which are 30 minutes apart, so its delay is somewhere between 0 and 15 minutes. If this task’s delay is 14 minutes, it runs at :21 and :51 every hour. Changing the schedule to a different minute moves the run time, and a delay is still added on top.
When a one-shot task runs early
A one-shot task scheduled for:00 or :30 runs up to 90 seconds early. Claude Code doesn’t shift a one-shot task scheduled for any other minute, so when the timing matters, schedule it off the hour and half hour: 3 9 * * * instead of 0 9 * * *.
Seven-day expiry
Recurring tasks automatically expire 7 days after creation. The task fires one final time, then deletes itself. This bounds how long a forgotten loop can run. If you need a recurring task to last longer, cancel and recreate it before it expires, or use cloud scheduled tasks or Desktop scheduled tasks for durable scheduling.Cron expression reference
CronCreate accepts standard 5-field cron expressions: minute hour day-of-month month day-of-week. All fields support wildcards (*), single values (5), steps (*/15), ranges (1-5), and comma-separated lists (1,15,30).
Day-of-week uses
0 or 7 for Sunday through 6 for Saturday. Extended syntax like L, W, ?, and name aliases such as MON or JAN is not supported.
When both day-of-month and day-of-week are constrained, a date matches if either field matches. This follows standard vixie-cron semantics.
Disable session-scoped scheduled tasks
SetCLAUDE_CODE_DISABLE_CRON=1 in your environment to disable the scheduler entirely. The cron tools and /loop become unavailable, and any already-scheduled tasks stop firing. See Environment variables for the full list of disable flags.
Limitations
Session-scoped scheduling has inherent constraints:- Tasks only fire while Claude Code is running and idle. Closing the terminal or letting the session exit stops them firing. Backgrounding the session carries
/looptasks over to a background session, which keeps running without a terminal. - No catch-up for missed fires. If a task’s scheduled time passes while Claude is busy on a long-running request, it fires once when Claude becomes idle, not once per missed interval.
- When you resume a session with
claude --resumeorclaude --continue, Claude Code restores the tasks scheduled withCronCreate, except recurring tasks that have expired and one-shot tasks whose scheduled time has passed. A self-paced/loopisn’t restored, so run/loopagain to restart it. Background Bash and monitor tasks are never restored on resume. - With feature-flag fetching off, Claude Code stores a task you asked to keep across sessions in the project’s
.claude/scheduled_tasks.jsonfile. When the.claudedirectory or that file is a symlink, Claude Code returns an error instead of scheduling the task. A saved task runs only in the project folder where you created it. If you copy the file into another folder, such as a new worktree, sessions there list the copied tasks but don’t run them, so create the task again in that folder.
- Cloud scheduled tasks: run in the cloud on a schedule, via API call, or on GitHub events
- GitHub Actions: use a
scheduletrigger in CI - Desktop scheduled tasks: run locally on your machine