Loops and Autonomous Runs: /loop, Iteration, and Scheduling

If none of those hold, a single call is cleaner and cheaper. Do not loop just because you can. "Refactor this function" is one call. "Refactor every function until the linter is silent" is a loop.

The /loop command in Claude Code

Claude Code runs in your terminal and already has access to your files, your shell, and your git history. The /loop slash command tells it to repeat a task rather than run it once.

There are two flavors:

Self-paced iteration runs the task, checks a condition, and decides whether to run again. This is the "keep going until X" pattern. Claude does the work, evaluates its own output against the stop condition, and either continues or stops.

Interval iteration runs the task on a delay: do the thing, wait N seconds or minutes, do it again. This is the polling pattern, useful when you're waiting on something outside your control (a CI run, a deploy, an external APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.View full definition →).

The shape of the command is a task plus a stop condition plus a budget:

Notice three things baked into that prompt. The task is explicit (run pytest, fix code). The stop condition is unambiguous (all tests pass). And there's a hard cap (10 iterations) so a stubborn bug cannot spin forever.

Why the stop condition must be machine-checkable

"Fix the code until it looks good" is not a loop condition. Claude has no objective signal to check against, so it will either stop arbitrarily or keep polishing forever. "Fix the code until pytest exits 0" is checkable: the exit code is a fact, not a judgment.

Good loop conditions are things a command can answer:

• pytest exit code is 0
• npm run build succeeds
• git status shows no uncommitted changes
• a specific string appears in a log file
• an HTTP endpoint returns 200

Anytime you can express "done" as a command that returns success or failure, you have a loop you can trust to stop on its own.

The worked example: keep fixing until the suite is green

This is the canonical use case, so let's make it concrete. You have a test suite with a handful of failures after a messy merge. You want Claude to iterate: run tests, read what broke, patch the source, run again, until the whole suite is green.

Read the guardrails hidden in that prompt. Step 3 forbids the single most common cheat an autonomous agent will reachreachThe number of unique people exposed to your message in a given period. Unlike impressions, reach counts each person once, no matter how often they see it.View full definition → for: deleting the failing test. Left unconstrained, a model asked to "make tests pass" may well decide the fastest path is to remove the test. The instruction "fix the SOURCE code only, never edit tests" closes that door.

The commit-per-fix instruction matters too. It gives you a clean git history to review and an easy revert if one of Claude's fixes was wrong. When the loop ends, you review the diff, not the process.

This is exactly the kind of task where the loop earns its keep. A single call would fix one round of failures and stop, likely revealing a second round it never touched. The loop grinds through all of it while you do something else.

Guardrails for unattended runs

The moment a loop runs without you watching each step, it can do damage or waste money at machine speed. Three guardrails are non-negotiable.

1. A hard budget

Every loop needs a ceiling that does not depend on the model's judgment. Iteration count is the simplest (--max-iterations). You can also cap wall-clock time or set a tokentokenA token is the basic unit of text that language models process, often a word fragment, whole word, or punctuation mark rather than a single character.View full definition → budget so a runaway loop hits a wall before it hits your bill. The budget is a backstop for when the stop condition never triggers, because sometimes the tests genuinely cannot be made to pass, and you want the loop to give up and tell you, not to keep trying forever.

2. A clear stop condition

Covered above, but it belongs on the guardrail list because it is the primary safety mechanism. The budget is the backstop; the stop condition is the intended exit. A loop with a budget but no real stop condition just burns to the cap every time.

3. A human review gate

For anything that changes state (writes code, pushes commits, sends messages, calls a paid APIAPIApplication Programming Interface: a standardised interface that lets applications communicate and exchange data without knowing each other's internal workings.View full definition →), decide in advance where a human signs off. Two common patterns:

• Review at the end. The loop runs fully autonomously but only produces a branch and a diff. You review before merging. This is the green-tests example: commits pile up on a branch, nothing ships until you say so.
• Review per action. You configure Claude Code's permission prompts so risky operations (file writes outside a directory, shell commands, network calls) require your approval each time. Slower, but appropriate when the blast radius is large.

You control this through Claude Code's permission settings. Constrain what tools the agent may use and which directories it may touch before you let it run unattended. The Claude Code documentation covers permission modes and tool configuration in detail.

A useful mental rule: the more autonomous the run, the tighter the sandbox. A loop you watch can have broad permissions. A loop that runs at 3am while you sleep should be able to touch almost nothing except the one thing it's there to do.

Scheduling: loops that fire on a cadence

Iteration answers "repeat until done." Scheduling answers "run again later, on a rhythm." A recurring digest, a nightly dependency check, a weekly report: these are not loops that spin until a condition, they are tasks that wake up on a schedule.

Claude Code itself does not run a background daemon. You schedule it the same way you schedule any command-line tool: with your operating system's scheduler (cron on Linux and macOS, Task Scheduler on Windows) or a CI runner like GitHub Actions.

Here's a nightly repo digest as a cron entry that runs Claude in non-interactive (headless) mode:

# Every weekday at 8:00 AM, summarize overnight git activity
0 8 * * 1-5 cd /home/me/project && \
  claude -p "Summarize commits from the last 24 hours grouped by \
  author. Flag anything touching auth/ or billing/. Output markdown." \
  >> ~/digests/daily-$(date +\%F).md 2>&1

The -p flag runs a single prompt and exits, which is exactly what you want for a scheduled job: no interactive session, deterministic start and finish, output redirected to a file. Pair this with a connector or an MCP server and the same scheduled run could post that digest to Slack or open a GitHub issue.

For scheduling that lives with your repo rather than one machine, GitHub Actions is the natural home. Anthropic's official GitHub integration lets you trigger Claude on a schedule or on repo events (a new PR, an issue labeled a certain way). A weekly on: schedule workflow that runs Claude to audit dependencies and open a PR is a clean, reviewable, scheduled autonomous run.

Scheduled runs need the same guardrails, more so

A scheduled job is autonomous by definition: nobody is watching when it fires. Everything from the guardrails section applies double. Give it a budget, give it a stop condition even for a one-shot digest (so a hung external call doesn't leave it running), and route anything that changes state through a review gate. A scheduled run that opens a PR is safe. A scheduled run that pushes to main is a foot-gun waiting for a bad night.

Iteration versus scheduling versus a single call

Quick decision guide:

• Single call: one task, no repetition, you're present. "Refactor this module."
• /loop (self-paced): repeat until a checkable condition, improving each pass. "Fix until tests pass."
• /loop (interval): repeat on a delay, waiting on something external. "Poll the deploy every 30s until live."
• Scheduled run: wake up on a cadence, usually a fresh single task each time. "Every morning, digest the repo."

The most powerful setups combine them: a scheduled workflow that fires nightly and, inside that run, loops until its dependency upgrades pass CI. Cadence on the outside, iteration on the inside.

Key Takeaways

• Loop only when the task repeats and "done" is machine-checkable. If you cannot express the stop condition as a command that returns success or failure, you don't have a safe loop yet.
• Every unattended loop needs three guardrails: a hard budget (iterations, time, or tokenstokensA token is the basic unit of text that language models process, often a word fragment, whole word, or punctuation mark rather than a single character.View full definition →), a clear stop condition, and a human review gate on anything that changes state.
• Constrain the agent to the cheat. "Make tests pass" invites deleting tests; say "fix source only, never edit tests" and commit each fix so you review a clean diff, not a black-box process.
• Schedule with the tools you already have: cron, Task Scheduler, or GitHub Actions running claude -p in headless mode. Claude Code is the worker, not the scheduler.
• The more autonomous the run, the tighter the sandbox. A loop you watch can have broad permissions; one that runs while you sleep should be able to touch only the one thing it exists to do.