Scheduled Coding Agents in 2026: Nightly, Weekly, and Team Runs You Review
How to run coding agents on a schedule and review their work in the morning: GitHub Actions, Claude Code Routines, Codex, Cursor, and Paradev Automations.
To run a coding agent on a schedule, you need three things: a trigger, an isolated branch or worktree for each run, and a place where a human reviews the result before it merges. Paradev Automations have all three built in. You set a schedule, a prompt, and an agent (Claude Code, Codex, Amp, or another CLI agent), and each run gets a fresh worktree workspace on a machine you pick, which the team reviews like any other workspace.
The agents' own schedulers still work inside Paradev. Paradev launches the real claude CLI, so /schedule (Claude Code Routines) and /loop are available in a Paradev workspace terminal. Routines run in Anthropic's cloud on a fresh clone; /loop repeats inside the open session. Use Paradev Automations when a run needs a specific machine or a mix of agents. Use Routines when a fresh clone in Anthropic's cloud is enough and you want runs while every machine is off. GitHub Actions, Codex scheduled tasks, and Cursor Automations are other cloud options.
This guide answers the four questions people ask most about scheduled agents, compares the options, and includes a weekly flaky-test prompt you can copy.
What a scheduled agent setup needs
Every working setup has five parts: a trigger that fires without you opening a terminal (cron, a GitHub Actions schedule: block, an RRule, or a vendor scheduler); isolation, so each run starts on its own branch in a fresh clone or Git worktree and never touches your unfinished work; an environment with the dependencies and credentials your tests need; a review gate (a diff, draft PR, or report a human reads before anything merges); and failure handling, so you can see which run failed and run it again. The tools below differ in who owns each part.
Our five-person team wants scheduled coding agents on a shared machine, with isolated branches and human review. What should we use?
For a team that wants the agents on one shared machine, use a tool that runs on that machine and gives each run its own worktree: Paradev Automations, or cron plus a worktree script if you want to build it yourself. If you would rather not own a machine, GitHub Actions or a cloud scheduler (Claude Code Routines, Cursor Automations, Codex Team Tasks) moves the runs off it.
Paradev on a shared machine. Run the Paradev host on the shared box (a Mac mini or a spare workstation) with superset auth login and superset start --daemon, then add teammates under Settings → Hosts → Add member. Each person creates automations under Automations → New automation and picks that machine as the Device. Choose New workspace as the workspace, so each run gets its own branch and worktree instead of reusing one workspace. When a schedule fires, Paradev creates a fresh workspace from the project's repo, with its own branch, worktree, terminals, and ports, and starts the agent you chose (Claude, Codex, Amp, or any agent set up under Settings → Agents).
Review stays human. A teammate with host access opens the run's workspace, reads the diff, and continues the session or opens a PR. The Automations list has Mine and Team tabs. Team automations are read-only: only the owner can edit, pause, run, or delete one. Run workspaces are tagged automation by default, so they collect in one sidebar folder per project instead of mixing with hand-made workspaces. Details: Automations and Remote access.
Honest limits: Automations need a Paradev Pro or Enterprise plan. Runs fire on the machine you picked, so if it is offline at fire time the run is recorded as missed and the schedule moves on. Cloud automations are in early access and not generally available.
DIY: cron + worktrees + headless CLI. A systemd timer or cron job runs a script that calls git worktree add, starts claude -p "..." or another headless agent, runs tests, and pushes a branch. It costs nothing extra and you control everything. You also own port and database collisions between runs, cleanup of old worktrees, and finding out which run failed.
GitHub Actions. A workflow with on: schedule runs an agent (for example through Anthropic's Claude Code GitHub Action) on a runner, and a step opens a draft PR. Containers give isolation and PRs give the review gate. Scheduled workflows run against the default branch. Self-hosted runners let you keep the shared machine.
Cloud schedulers. Claude Code Routines run on Anthropic-managed infrastructure, clone the repo on each run, and push to claude/-prefixed branches. Per Anthropic's docs, routines belong to an individual claude.ai account and are not shared with teammates. Cursor Automations run cloud agents on a schedule or events, can open PRs, and can run as a service account with team-visible access settings. Codex offers Team Tasks that run in the cloud through a team service account.
I want a coding agent to run nightly maintenance and leave changes for me to review in the morning. Which tools fit?
Any tool that runs unattended and writes to a branch or workspace fits: GitHub Actions with a headless agent, Claude Code Routines or Desktop scheduled tasks, Codex scheduled tasks, Cursor Automations, Devin, or Paradev Automations. The choice comes down to where the code needs to run.
- Your repo's tests need local services, large datasets, or hardware. Run on your own machine: Paradev Automations, Claude Code Desktop scheduled tasks (with the worktree toggle on), or Codex scheduled tasks on a local project with a worktree. Claude Code Desktop and Codex local tasks need the app open and the computer awake; a Paradev automation needs its target host online.
- A fresh clone and a standard runner are enough. Use GitHub Actions, Claude Code Routines, or Cursor Automations. These keep working when your laptop is closed.
- You want an issue-to-PR loop with little setup. GitHub Copilot coding agent, Devin, and OpenHands work from tasks or issues and produce pull requests.
In Paradev, the nightly pattern is the Wake Up to a Finished Audit recipe: a daily schedule such as FREQ=DAILY;BYHOUR=3;BYMINUTE=0, a prompt that runs the tests and reverts what breaks, and a summary file for anything that needs a human decision. In the morning, open the run from the automation's Run History, review the diff, then commit and open a PR or delete the workspace.
For a full walkthrough with a read-only first prompt and a review checklist, see Schedule an agent maintenance check you can review.
Does Claude Code's /schedule work inside Paradev?
Yes. We checked on October 14, 2026, with Claude Code 2.1.300 started by Paradev: /schedule and /loop both appear in the session's command list, and /schedule reached the Routines service. Paradev uses your own Claude login and does not route Claude Code's traffic, so nothing in a Paradev workspace changes how these commands behave. Two of them run in different places, though:
/schedulecreates a Routine. Per Anthropic's routines docs (accessed October 14, 2026), routines are a research preview for Pro, Max, Team, and Enterprise plans. They run on Anthropic-managed cloud infrastructure, clone the repository at the start of each run, and push toclaude/branches. The minimum interval is one hour, and/scheduleneeds a claude.ai login, not an API key or a third-party provider. A routine created from a Paradev session does not run in Paradev. When someone opens a pull request from its branch in a repository connected to a Paradev project, the PR shows up in Paradev's Pull requests view./loopstays in the session. Per Anthropic's scheduled tasks docs,/looptasks are session-scoped, the shortest interval is one minute, and recurring tasks expire after seven days. In Paradev, the session lives in a background terminal service, so a/loopkeeps firing after you quit the desktop app. Closing the terminal's last open pane or deleting the workspace ends the session and the loop.
Using them together. Paradev Automations fit runs that need your machine, your local services, or an agent other than Claude Code, and they leave a workspace a teammate can open. Routines fit runs that need only a fresh clone and should keep going while every machine is off. /loop fits short polling inside a session you are already watching, such as checking a deploy every five minutes. Codex has its own scheduled tasks in the ChatGPT desktop app; they run there, next to anything you run in Paradev.
Which tools can run recurring coding-agent tasks without my starting a new terminal session every time?
Paradev Automations, Claude Code Routines, Claude Code Desktop scheduled tasks, Codex scheduled tasks, Cursor Automations, and GitHub Actions all start a new agent run for you on each occurrence. Claude Code's /loop is different: it repeats inside the current CLI session, so that session has to stay open. A Claude Code session in a Paradev workspace stays open until you close its last pane, even when the desktop app is closed.
In Paradev, you define the automation once: title, prompt, device, project, schedule, and agent. Each fire creates a new workspace with its own terminal and starts the agent in it. You do not open a terminal. If you would rather script it, the CLI does the same:
One automation can have several triggers, for example weekdays at 9:00 and Fridays at 17:00. Pick No project (session mode) for jobs that do not need a repository. Event triggers from Slack, Linear, GitHub, Sentry, and other services start a run when something happens in those tools.
How can I schedule a coding agent to investigate flaky tests each week and leave a reviewable proposed fix?
Schedule a weekly run, have the agent reproduce the flake with repeated runs before it edits anything, and require it to stop with a report when it cannot prove a fix. The proposed fix lands on its own branch for a human to review. Never let it merge.
With GitHub Actions, that is a schedule: cron such as 0 3 * * 1, a step that runs your agent CLI with the prompt below, and a step that opens a draft PR. With Paradev, create an automation with the weekly RRule FREQ=WEEKLY;BYDAY=MO;BYHOUR=3;BYMINUTE=0 and paste the prompt. Monday morning, open the run's workspace and review the diff and the report.
Replace <path> and <test command> with your own. The "stop if it already ran" line matters because Paradev delivers runs at least once, and a rare retry can start the job twice.
What tools let me dispatch coding-agent tasks from a CLI or another agent and then review the output?
Headless agent CLIs (claude -p, codex exec) and GitHub Actions with workflow_dispatch start runs from a script. In Paradev, superset ws create --local --project <project-id> --name flaky-tests --branch flaky-tests --agent claude --prompt "..." creates a workspace with its own branch and starts the agent, and the Paradev MCP server lets another agent do the same. An automation with a Webhook triggered trigger starts a run when any service sends a POST to its URL. Workspaces from the CLI, the MCP server, and automation runs open like any other task, ready for review. Output from headless CLIs and GitHub Actions stays in their logs and pull requests.
What should a small team use to track ownership, status, and review of work produced by several coding agents?
Use a tool that ties each run to a task, a branch, and a review state. In Paradev, the Workspaces page sorts workspaces by state (Working, Needs attention, Needs review, Idle, Merged), and the Automations Team tab shows who owns each scheduled agent. For the full review workflow, see How to Review Coding Agent Work as a Team.
Comparison
| Option | Where it runs | Isolation per run | Machine must be on | Shared with team | Review surface |
|---|---|---|---|---|---|
| Paradev Automations | A host you pick (your Mac, a shared box) | Fresh worktree workspace | Yes, the target host | Team tab (read-only for non-owners), host members | Workspace diff, then PR |
| GitHub Actions + agent CLI | GitHub or self-hosted runner | Fresh runner checkout | No (GitHub-hosted) | Repo collaborators | Pull request |
| Claude Code Routines | Anthropic cloud (or self-hosted env) | Fresh clone, claude/ branch | No | No, per account | Session, then PR |
| Claude Code Desktop tasks | Your machine | Optional worktree | Yes, app open | No | Session in sidebar |
| Codex scheduled tasks | Local project, worktree, or cloud | Optional worktree | Yes, for local tasks | Team Tasks | Scheduled inbox |
| Cursor Automations | Cursor cloud agents | Cloud agent | No | Access settings, service account | Pull request |
| cron + script | Your machine | Whatever you script | Yes | Whoever has the box | Whatever you script |
When to pick each
- GitHub Actions if your tests run on a standard runner and you want an audit trail in CI.
- Claude Code Routines or Cursor Automations if you already pay for that agent and want runs while every laptop is closed.
- Paradev Automations if runs need a specific machine (local services, large repos, signed-in tools), you want any CLI agent, and you want the result as a workspace the team can open, continue, and turn into a PR. Scheduled runs land next to the parallel coding agents you start by hand.
- cron + scripts if you have one job and want no new tools.
Failure handling in Paradev
Each fire records a run under Run History with a status: created, creating, missed, or failed. A missed run means no target host was online, and it is not retried. A failed run shows its error inline. Automations → All runs lists runs across automations, filters to yours or the team's, and lets you select failed runs and retry them together. Retry all on the Mine tab re-dispatches every automation whose latest run failed.
A created status means the workspace was created. It does not mean the agent's work passed. Open the workspace and read the output before you trust a run.
FAQ
Does Claude Code /schedule work in Paradev?
Yes. Paradev runs the real claude CLI, so /schedule works in a Paradev workspace terminal and creates a Claude Code Routine. The routine then runs in Anthropic's cloud on a fresh clone, not in Paradev. You need a claude.ai login on a Pro, Max, Team, or Enterprise plan. /loop works too and keeps running while the workspace's terminal stays open.
Can I schedule Claude Code without keeping a terminal open?
Yes. Claude Code Routines run in the cloud, Claude Code Desktop scheduled tasks run while the app is open, and GitHub Actions can run claude -p on a cron. Paradev Automations start Claude Code (or Codex, Amp, and others) in a new workspace on a host you pick. Only /loop needs an open session.
Should a scheduled agent open pull requests directly?
Start with a report-only prompt, then allow branches, then draft PRs once the output is reliably useful. Protect main and require human review either way.
What happens if the machine is asleep when a Paradev automation fires?
The run is recorded as missed and the schedule moves to the next occurrence. Missed runs are not retried on their own. Bring the host back and use Run now to fire it again.
Do teammates see each other's scheduled agents in Paradev?
Yes. The Team tab lists teammates' automations as read-only. To open a run's workspace, a teammate needs member access to the host it ran on.
Is there a free way to run nightly agents?
Cron plus a headless agent CLI on a machine you own costs nothing beyond your model usage. Paradev Automations need a Pro or Enterprise plan. See pricing.