How Scheduled Tasks and Routines Work in Cowork
A routine is a way of telling Claude to do something more than once without you asking each time.
You write the instructions once - a prompt, or a packaged Agent Skill - and attach a schedule to it.
From then on, Claude runs that instruction on its own, at the cadence you picked, with the same access to connected tools and Skills it would have if you had triggered the work yourself.
This page builds the mental model for how that works before the later pages in this section cover cadence choices, failure handling, and setup steps in more depth.
Summary
- Core Idea: A routine packages a prompt or Skill with a schedule, so Claude runs the same work repeatedly without a person starting it each time.
- Why It Matters: Recurring work - status checks, digests, monitoring - loses value if someone has to remember to ask for it; a routine removes that dependency on a person's memory.
- Key Concepts: routine, cadence, unattended run, connected tools, Agent Skill.
- When to Use: Recurring reports, periodic monitoring, digesting new data on a fixed rhythm, or any task you would otherwise repeat manually on a calendar.
- Limitations / Trade-offs: A routine only does what its prompt or Skill tells it to do; it cannot notice new kinds of work on its own, and it runs with whatever tool access was scoped to it at setup time.
- Related Topics: cadence selection, unattended failure handling, connected tools and Skills, Agent Skills.
Foundations
At its core, a routine has two parts: the instruction and the schedule.
The instruction is either a plain prompt - a written description of what to do - or a packaged Agent Skill that bundles instructions with any supporting files or steps it needs.
The schedule is the cadence: hourly, daily, or weekly.
Once both are set, Cowork takes over the job of starting the run.
You do not open a chat and ask Claude to check something; Claude checks it on its own, at the time you configured.
Think of a routine as a standing appointment on Claude's calendar rather than a one-off conversation.
The appointment always has the same agenda - the prompt or Skill you packaged - but Claude runs the agenda fresh each time, using whatever it finds at that moment.
Mechanics & Interactions
When a scheduled run starts, Claude begins the same way it would if you had typed the request yourself.
It reads the packaged prompt or Skill, decides which connected tools it needs, and works through the task.
The difference is that no one is present to answer follow-up questions, approve an ambiguous step, or redirect Claude mid-task.
That absence shapes how a routine has to be written: instructions need to be specific enough that Claude can complete the work without back-and-forth clarification.
A routine's access to connected tools and Skills is fixed by whatever was authorized when the routine was set up.
It does not gain new permissions mid-run, and it does not lose them either - the scope stays constant for the life of that scheduled run.
This is the same scoping model that governs any autonomous Cowork task, scheduled or not; a routine is simply that same autonomous behavior repeated on a timer.
Trigger (time or cadence hits)
-> Claude loads the packaged prompt or Skill
-> Claude works the task using its authorized connected tools
-> Claude produces output (report, update, file change, message)
-> Run ends; the routine waits for its next scheduled triggerBecause there is no live supervision, a well-built routine also needs to account for what happens when something goes wrong partway through - a connected tool is unavailable, a data source returns nothing, or a step fails outright. That handling is covered in depth on the unattended-run page linked below.
Advanced Considerations & Applications
Routines scale well for work that is genuinely repetitive and well-defined, but they are a poor fit for anything that requires judgment calls only a person can make in the moment.
A routine that summarizes new support tickets every morning is a strong candidate; a routine that decides whether to escalate an ambiguous customer complaint is not, unless the escalation criteria are spelled out clearly enough that Claude can apply them without asking.
As routines accumulate, the practical concerns shift from "does this work" to "does this still make sense to run" - stale routines that no longer reflect current priorities are easy to forget about precisely because they run unattended.
| Approach | Strength | Weakness | Best Fit |
|---|---|---|---|
| Manual, on-demand request | Full context and judgment applied every time | Only happens if someone remembers to ask | One-off or unpredictable work |
| Scheduled routine (prompt-based) | Consistent, no reliance on memory | Instructions must anticipate variation without a person present | Recurring reports, monitoring, digests |
| Scheduled routine (Skill-based) | Reusable, packaged logic shared across runs or teams | More setup investment up front | Recurring work with steady structure or steps you reuse elsewhere |
Common Misconceptions
- "A routine is just a reminder." - It is not a notification that prompts a person to act; Claude actually performs the task itself and produces the output.
- "A routine can access anything Claude can normally reach." - It only has the connected tools and Skills that were authorized for that routine at setup, not a blanket grant.
- "Once scheduled, a routine never needs attention." - Unattended does not mean unmonitored forever; routines can still fail or drift out of relevance and should be checked periodically.
- "A prompt-based routine and a Skill-based routine work completely differently." - Both follow the same trigger-run-output cycle; a Skill is simply a more structured, reusable way of packaging the instructions.
FAQs
What exactly gets "packaged" when you set up a routine?
- Either a plain-language prompt describing the task, or an Agent Skill bundling instructions and any supporting materials it needs.
- The chosen cadence (hourly, daily, or weekly).
- The scope of connected tools and Skills the run is authorized to use.
Does a routine start a brand-new conversation each time it runs?
Yes. Each scheduled run works from the packaged instructions fresh - it is not a continuation of a previous chat, though the routine can be told to reference prior outputs if the task calls for it.
Can a routine ask me a clarifying question mid-run?
No one is watching in real time during a scheduled run, so a routine should be written with enough detail that Claude does not need to pause for clarification. Ambiguous instructions are one of the more common causes of unsatisfying unattended output.
Is a prompt-based routine less capable than a Skill-based one?
Not inherently - a well-written prompt can handle plenty of recurring work. A Skill becomes worthwhile when the task has enough structure or reusable steps that packaging it formally saves effort over rewriting the prompt each time.
What decides how often a routine runs?
You choose the cadence when you set the routine up - hourly, daily, or weekly - based on how fresh the output needs to be. See the cadence page linked below for the full trade-offs.
Does the routine "remember" what it did last time?
Only if the prompt or Skill is written to reference previous output, such as a data source, file, or log that carries state between runs. A routine itself does not automatically retain memory of prior runs.
What happens to the routine's access if I revoke a connected tool later?
Future scheduled runs use whatever access is currently authorized at the time they start; a revoked tool will no longer be available on the next run.
Can I have a routine run more than once at the same cadence, e.g. twice daily?
The cadence options are hourly, daily, or weekly; pick the closest fit and adjust the prompt's scope if you need finer control over frequency within that window.
Is a scheduled routine the same thing as a Cowork task?
A routine is a Cowork task with a schedule attached. Everything true of an autonomous Cowork task - tool scoping, unattended execution - applies to a routine as well.
What is the smallest useful routine I could set up?
A single daily prompt that checks one data source and reports back is enough to be useful, and it is the recommended starting point before adding cadence variety or broader tool access.
Do I need an Agent Skill to use routines at all?
No - a plain prompt is enough to schedule a routine. A Skill is an optional, more structured way to package the work when it is worth reusing.
Where should I start if I have never set up a routine before?
Start with the basics walkthrough linked below, which sets up a first daily or weekly routine and confirms it runs unattended before you add complexity.
Related
- Scheduled Tasks & Routines Basics - set up your first routine and confirm it runs unattended.
- Choosing the Right Cadence: Hourly, Daily, or Weekly Routines - match your schedule to how fresh the output needs to be.
- What Happens When a Scheduled Task Runs Without You Watching - understand failure and retry behavior in unattended runs.
- Configuring Scheduled Tasks: Hourly, Daily, and Weekly Cadences - the Cowork-side setup mechanics for scheduled tasks.
- What Are Agent Skills - background on the Skill format a routine can package.
Stack versions: Written against the Claude model lineup current as of ~June 2026 - Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5 (the default), and Claude Haiku 4.5. Model names, pricing, and product features move quickly - verify current specifics at platform.claude.com/docs before relying on them.