Claude Code Loops: Recurring Prompts That Actually Run

If you've ever wanted Claude Code to do something more than once without babysitting it, you've probably hacked together a shell loop or a cron job wrapping claude -p. That worked. Barely. Claude Code now has a first-class Loop feature that handles recurring prompts natively - scheduling, intervals, expiry, and session scoping built in.

This is the evolution of the "Ralph Wiggins technique" (yes, that was its name) into something you'd actually ship a workflow around.

Why Your Scheduled Tasks Keep Dying

The core problem with wrapping Claude Code in external schedulers: context evaporates between runs. Each invocation is a cold start. No memory of the last run. No awareness of what changed. No ability to pick up where it left off.

Loops solve this by keeping the session alive. The prompt runs on a schedule within a persistent Claude Code session. Same context window, same tool access, same MCP connections. The agent remembers what it did last iteration and can build on it.

Setting Up Your First Loop

Two entry points. Natural language or the /loop command.

Natural language works exactly how you'd expect:

Every 5 minutes, check if my PR build is passing. If it fails,
read the error log, fix the issue, and push a new commit.

Claude Code parses the schedule, sets the interval, and starts executing. You can also be explicit with the command:

/loop "Summarize any new posts tagged #announcements in the team Slack channel" --interval 30m --expires 8h

The minimum interval is one minute. Maximum window is three days. After the expiry, the loop stops automatically - no orphaned processes, no runaway API bills.

Each loop gets a scheduled prompt, optional notes for context, and the auto-expiry timer. Clean and predictable.

The Commands

Three new commands handle lifecycle management:

cron create    # Create a new scheduled loop
cron list      # See all active loops in the current session
cron delete    # Kill a specific loop by ID

cron list shows you every active loop with its interval, next run time, and expiry. cron delete takes the loop ID and stops it immediately.

Use Cases That Actually Matter

Fixing builds on repeat. Point a loop at your CI pipeline. Every few minutes, check the build status. If it's red, read the logs, identify the failure, fix it, commit, push. Keep going until green. This is the "leave it running overnight" play - wake up to a passing build instead of a Slack notification graveyard.

Slack channel summaries via MCP. If you've connected Slack through MCP, loop a prompt that pulls new messages from a channel, summarizes them, and writes the summary to a local file or posts it back to a different channel. Daily standup notes that write themselves.

Daily git recaps. Schedule a loop that runs once a day, pulls git log for the last 24 hours across your repos, formats a summary, and saves it to your desktop. Context on what your team shipped without opening GitHub.

Every day at 9am, run git log --since="24 hours ago" --oneline
across all repos in ~/Developer, summarize the changes by project,
and save to ~/Desktop/daily-recap.md

Combining Loops with Skills

This is where it gets interesting. Loops compose with everything Claude Code already has - skills, MCP tools, CLI access. Chain them together.

The Hacker News automation is a good example of this in practice:

1. Loop fires every morning
2. Firecrawl scrapes the HN front page
3. Claude summarizes the top stories relevant to your interests
4. Gmail CLI skill sends you the digest as an email

Every day at 7am, use Firecrawl to scrape the Hacker News front page.
Summarize the top 10 posts most relevant to AI agents and developer tools.
Email me the summary using the Gmail CLI skill.

One prompt. Four tools. Runs daily until the session closes or the expiry hits. No glue code.

Session Scope: The Big Caveat

Loops are scoped to the active session. Close the terminal, close the session, loops stop. This is by design - it keeps the feature safe and predictable. No background daemons, no orphaned processes eating your API quota at 3am.

But it means loops aren't durable. If you need something that survives a reboot or runs when your laptop is closed, you need a different approach:

• Claude Desktop app - has a scheduling feature that persists independently of terminal sessions
• GitHub Actions - for truly durable, cloud-based scheduling with Claude Code as a step

For anything that needs to run reliably for more than a working session, use those instead. Loops are for "I'm working and I want this thing happening in the background while I focus on something else."

The 10% Time Offset

A subtle but smart detail: Claude Code adds up to a 10% random offset to your scheduled interval. If you set a 10-minute loop, it might fire at 9:12, then 10:48, then 9:36.

Why? If a thousand developers all schedule a "every 10 minutes" loop, you don't want all of them hitting the API at exactly :00, :10, :20. The jitter spreads the load. Same principle as exponential backoff in distributed systems, applied preemptively.

You can disable this with a flag if you need precise timing, but for most use cases the offset is invisible and helpful.

Limitations Worth Knowing

• Session-bound. Already covered, but it bears repeating. No session, no loops.
• Minimum one-minute interval. You can't run a loop every 10 seconds. This is a rate-limit guardrail.
• Three-day maximum expiry. Even if your session stays alive, loops cap out at 72 hours.
• Disable flag available. If your org wants to prevent loop usage entirely, there's a flag to turn it off. Useful for teams where runaway automation is a concern.
• API costs accumulate. Each loop iteration is a full prompt execution. A 1-minute loop running for 8 hours is 480 API calls. Plan accordingly.

When to Use Loops vs. Cron vs. GitHub Actions

Loops - ephemeral, session-scoped, great for "while I'm working" background tasks. Zero setup.

System cron / LaunchAgents - durable, survives reboots, but you lose Claude Code's session context. Each run is a cold start.

GitHub Actions - cloud-durable, runs when your machine is off, integrates with repos natively. Best for CI/CD-adjacent automation.

Pick based on durability requirements. Most developers will use loops for the ad-hoc stuff and Actions for anything that needs to be reliable.

• Claude Code Loops in 7 Minutes - full walkthrough with live examples

Official docs:

• Claude Code Documentation - Anthropic's official Claude Code docs
• Claude Code Skills - composable skills that pair well with loops

This article is based on a Developers Digest video. All feature behavior is based on direct testing with Claude Code at time of publication.

Further Reading:

• Anthropic: Introducing Claude Code - official announcement and feature overview
• Claude Code Sub-Agents Guide - parallel agents that compose with loops
• Claude Code Worktrees - another Claude Code primitive for parallel development
• Firecrawl Documentation - web scraping tool used in the Hacker News automation example

Watch the Video