/schedule — cron in the cloud

Routines (research preview) that run on Anthropic’s cloud with your computer off — 1-hour minimum interval, plus GitHub-event and API triggers. Triage, docs sync, nightly audits.

/schedule creates routines — cron for Claude Code, running on Anthropic’s cloud with your computer off. The schedule examples below are the recurring jobs people actually run: morning issue triage, nightly test-and-report runs, weekly dependency audits, docs kept in sync after every merge. Minimum interval is an hour, and routines can also fire on GitHub events or API triggers, which is where they stop being timers and start being automation. Because a routine runs unattended, grades matter more here than anywhere else — check the safety grade before scheduling anything with write access. The schedule-examples guide covers cadence patterns; for a scheduled loop with budgets and stop conditions prewired, generate a harness in the builder.

Re-run PR review on schedule

Loop/schedule

Re-invoke a specific PR review skill every 20 minutes until the review completes or you stop it.

prompt
→ Claude
/loop 20m /review-pr 1234 , to re-run that skill each iteration. {/ min-version: 2.1.196 /}As of v2.1.196, a scheduled fire only runs skills that Claude is [allowed to invoke on its own](/en/skills#control-who-invokes-a-skill). The following reach Claude as plain text instead of executing
cimedium riskclaude-code
source ↗

README freshness check

Loop/schedulelooprepo

Once a week, verify every command, path, and badge in the README actually works against the current codebase and open a PR fixing anything stale.

prompt
→ Claude
/schedule every Friday at 3pm, verify the README: run each documented setup and usage command in a clean checkout, check that referenced files and scripts exist, and open a PR correcting anything that fails or has drifted, with a note explaining each fix
docsmedium riskclaude-codecodex

Keep docs in sync with main

Loop/schedule

On every push to main, check whether changed code drifted from the docs in /docs and open a PR fixing anything out of date.

prompt
→ Claude
/schedule on every push to main, check whether the changed code drifted from the docs in /docs, and open a PR fixing anything out of date
docshigh riskclaude-codecodex

Ship one post a week, learn what works

Loop/scheduleForward Future

Six weeks, one variable changed per post; measure replies, saves, and questions, and end with a winner or an honest null.

prompt
→ Claude
Find a repeatable weekly post format for [approved account, audience, and topic] through a six-week experiment. If the account, audience, or topic is missing, ask for it before drafting. Obtain approval before publishing anything externally. Each week, draft one short post about a real problem [person, product, or company] solves. Record substantive replies, saves, and questions after the same measurement window. Treat likes as secondary evidence. Keep the audience, topic area, cadence, and measurement window comparable. Change only one meaningful element each week, such as the opening, format, example, or call to action, based on the strongest signal from the previous post. Stop when one format materially outperforms the alternatives, the six-week experiment ends without a winner, approval is withheld, required metrics are unavailable, or the budget is exhausted. Never fabricate engagement data. Finish with every post, its measurements, the variables tested, the winning format or no-winner result, and the next recommendation.
contentlow riskclaude-codecodex

Drive work units unattended

Loop/schedule

Run claimed work units in order without prompts, deferring unclaimed tasks until the next cycle.

prompt
→ Claude
/goal /drive auto ok waits on. It asks one thing, and only when you are there to answer it : bare /drive is the attended form, which — when more than one unit is claimable or resumable — shows you the partition and asks once which units to take, drives them in the order you picked, and reports the rest as deferred (still claimable, so the run ends pending ). /drive auto is the unattended form, prompt-free at every step, and it is what the hourly routine and any /goal /drive auto ok loop invoke by name ( docs/drive-loop-runbook.md ); /drive night is a synonym of it. Which form runs follows from how you invoked it, never from a guess about whether anyone is watching. Nothing else is ever asked: not the partition, not each ticket. Approval is not a per-ticket prompt: it was given where the work was decided — a human merged the pull request that published the mission or ticket, and the merge policy recorded on it at creation says whether its completed units may merge unattended. Work is coordinated by the claim protocol — every runner reads the claims in flight from the unmerged remote branches, so two runners (or two machines) never pick the same work. There is no lock file and no server; the repository itself is the coordination medium |
automationmedium riskclaude-code

Catch schema drift nightly

Loop/schedulelooprepo

Every night at 3am, dump the production schema and diff it against migrations, filing issues for any drift found.

prompt
→ Claude
/schedule every night at 3am, dump the live database schema (`pg_dump --schema-only`) and diff it against the schema produced by applying all committed migrations to a fresh scratch database. Verify the scratch build reports `migrate status` clean before comparing. Any drift — columns, indexes, or constraints present in prod but missing from migrations, or vice versa — gets an issue filed with the exact diff attached and a proposed corrective migration for human review. Read-only against production; never modify the live schema. Stop after 1 pass per run.
databaselow riskclaude-code

Weekly dependency vulnerability audit

Loop/schedulelooprepo

Every Monday morning, run the dependency vulnerability audit, open one PR fixing what auto-fix can handle safely, and file issues for the rest.

prompt
→ Claude
/schedule every Monday at 8am, run `npm audit`, open a single PR applying only non-breaking fixes with tests passing, and file one issue per remaining high or critical advisory with its CVE link and affected paths
securitymedium riskclaude-codecodex

/goal + Routines overnight combo

Loop/scheduleSabrina Ramonov

The two-layer answer to how do I run this overnight: /goal drives in-session work to done, while a scheduled Routine keeps recurring unattended work running on Anthropic's cloud with your laptop closed.

prompt
→ Claude
/schedule a Routine (runs on Anthropic cloud, laptop closed) for recurring unattended work, and use `/goal` for in-session iterate-to-done — the two-layer overnight pattern. Guardrails: Stop when the goal is verifiably met, or stop after 15 iterations, whichever comes first. Verify each pass by running the relevant tests or checks — self-reported success does not count. Keep changes minimal and never touch files outside the task’s scope.
automationmedium riskclaude-code

Draft weekly release notes

Loop/schedulelooprepo

Every Friday at 2pm, draft release notes from merged PRs into releases/DRAFT.md and verify all links resolve.

prompt
→ Claude
/schedule every Friday at 2pm, draft release notes from the PRs merged since the last draft: group changes into features, fixes, and docs, write one plain-English line per change with the PR link, and save to releases/DRAFT.md. Draft only — a human edits and publishes; never post or send anywhere. Verify every PR link resolves and every merged PR since the last run is covered before saving. Stop after 1 pass per run.
automationlow riskclaude-code

→ run /audit-skills every Monday morning

Loop/schedule

Community schedule loop for security, sourced from github. Verified exit condition, evaluator-gated.

prompt
→ Claude
/schedule → run /audit-skills every Monday morning Guardrails: Stop when the goal is verifiably met, or stop after 15 iterations, whichever comes first. Verify each pass by running the relevant tests or checks — self-reported success does not count. Keep changes minimal and never touch files outside the task’s scope.
securityhigh riskclaude-code
source ↗
Sponsored · ConnectMyEmail

Loops that read your inbox.

Email is the missing tool in your harness. ConnectMyEmail gives Claude Code and Codex a clean MCP into Gmail, Outlook, iCloud and IMAP — triage, drafts, follow-ups, on a loop.

connectmyemail.com →

Inbox-zero weekly sweep

Loop/schedulelooprepo

A scheduled Friday pass that archives read newsletters, trashes spam, and surfaces what needs a reply — protecting unread human mail.

prompt
→ Claude
/schedule every Friday at 5pm, run an inbox-zero pass on my email with the ConnectMyEmail MCP — archive read newsletters, move spam to Trash, and surface anything that needs a reply, never permanently deleting mail and never touching unread human messages. Stop after 300 messages per run, verify the unread count dropped, and ask before archiving anything ambiguous.
emailmedium riskclaude-codecodex