Guides Claude

How To Use Claude To Find What's Actually Eating Space on Your Computer

Learn how to use Claude as a storage-cleanup copilot for your Mac so you can identify what is actually taking up space before deleting random folders.

intermediate 5 steps

Introduction

Learn how to use Claude as a storage-cleanup copilot for your Mac so you can identify what is actually taking up space before deleting random folders. You will investigate large directories, review common developer clutter, and turn the cleanup process into a reusable monthly checklist.

Ask Claude to preview the impact before running cleanup commands. Do not run cleanup commands just because they look standard.

Step-by-step 5 steps

Instructions

  1. Step 1 of 5

    Investigate Before You Delete Anything

    Start a new Claude session and make the safety rule explicit: you want help investigating first, not deleting first. The point is to have Claude explain what is large, what it likely contains, and what is usually safe to remove before any destructive command gets suggested.

    Prompt
    Help me investigate what's taking up storage on this Mac. Start by identifying the biggest directories in my home folder. For each large folder, explain what it likely contains, whether it's usually safe to delete, and what questions I should answer before removing anything. Do not suggest destructive commands until we've reviewed the findings.

    Once Claude gives you commands, run them in Terminal and paste the results back in. This gives Claude real local information to work from instead of vague guesses.

    Pro tip: The built-in Mac storage screen is useful for broad categories, but it often misses the real story. The problem is usually not one huge file. It is a pile of medium-size directories, old dependencies, and app caches that add up fast.
  2. Step 2 of 5

    Find Old node_modules and Other Reproducible Bloat

    If you do any kind of web development, node_modules is usually one of the first places to check. Old experiments, abandoned repos, and half-finished client work can each carry hundreds of megabytes or several gigabytes of dependencies.

    Prompt
    Scan my dev folders for large node_modules directories. Show me the largest ones, where they live, and when they were last modified. Separate them into: 1. likely safe to remove because the project looks old or inactive 2. review manually because the project may still be active Explain your reasoning for each one.

    This is one of the easiest cleanup wins because you are usually deleting installed dependencies, not your source code. If a project is old and you need it later, you can reinstall everything with npm install.

    Pro tip: If you do not know which projects are still active, ask Claude to interview you. It can walk through the list one folder at a time and help you decide what is stale.
  3. Step 3 of 5

    Clean Up Homebrew and Other Tooling Cache Carefully

    After node_modules, move on to package-manager and tooling clutter. Homebrew is a common offender because it accumulates old downloads, outdated package versions, and dependencies you no longer need. Docker can do the same thing with images, containers, and build cache.

    Prompt
    Explain how to safely clean up Homebrew on this Mac. Tell me what old versions, caches, or unused dependencies are taking space, what the normal cleanup commands would do, and which ones are low-risk versus which ones need manual review first.
    Prompt
    Help me find Docker files, images, and caches that are taking significant space on this Mac. Show me what is low-risk to remove, what needs review first, and how much space each cleanup might save.

    The habit that matters is asking Claude to preview the impact first. Do not run cleanup commands just because they look standard.

  4. Step 4 of 5

    Clear Claude Cache Without Deleting the Wrong Thing

    App cache is another easy place to reclaim space, and the Claude cache can get surprisingly large. During setup for this guide, the cache had grown to around 15 GB, much of it tied to Claude Cowork usage.

    Open the Claude desktop app and click Help > Troubleshooting > Clear Cache and Restart. You can also click Delete Cowork VM Bundle and Restart. That deletes virtual coding sandboxes that Claude Cowork has used.

    Do not click Delete Cowork VM Sessions and Restart, as that will delete all your Claude Cowork threads.
    image-2141
    Pro tip: This same logic applies to other local AI apps too. If you use ChatGPT desktop, Codex, or similar tools heavily, their local caches may be much larger than you think.
  5. Step 5 of 5

    Turn This Into a Reusable Monthly Cleanup Checklist

    The bigger win here is not just getting space back once. It is creating a repeatable cleanup workflow so you do not end up rage-deleting files the next time your disk fills up.

    When you finish the audit, ask Claude to turn your process into a reusable Claude skill.

    You can also ask Claude to create a checklist in a markdown skill file so you can manually track the same process every month.

You're done

That's the whole workflow

Mark it complete to save your progress. Background and answers to common questions follow below.

Keep going

Keep learning with Rundown Pro

A guide shows you one workflow. Pro opens the full course library, so you can learn the whole system behind it.

  • Every on-demand course
  • Certifications on completion
  • Group office hours and member perks

$29/mo, cancel anytime

Overview Back to the steps

Background and context

Who This Is Useful For

  • Operators, founders, and freelancers who use AI tools on their main computer and keep running into storage warnings
  • Developers and vibe coders with old repos, large node_modules folders, Homebrew clutter, or app caches they do not fully understand
  • Mac users who want to free up space without blindly deleting files and breaking a working setup

What You Will Build

You will build a Claude-assisted storage audit workflow that ranks the biggest storage offenders on your machine, separates low-risk cleanup targets from items that need review, and becomes a reusable monthly cleanup checklist.

  • A ranked view of large folders and likely storage offenders
  • A review of common cleanup categories like node_modules, Homebrew cache, Docker clutter, and Claude desktop cache
  • A repeatable monthly checklist or Claude skill for future storage audits
image-2140

What You Need

  • Access to Claude or another LLM that can help with coding
  • A Mac you want to audit for storage usage
  • Terminal access so you can run Claude’s suggested investigation commands and paste the results back in
  • Optional: development folders, node_modules directories, Homebrew, Docker, or Claude desktop cache to review

Going Further

  • After the first audit, reuse the workflow monthly and expand it to other non-obvious storage eaters that often build up when you code with AI.
  • Python environments like .venv folders and old conda environments
  • Xcode simulators and derived data if you do Apple-device development
  • Downloads filled with installers, ZIP archives, models, and exports
  • Screen recordings and generated media from Loom, CleanShot, or AI video tools
  • Package-manager caches from npm, pnpm, yarn, or pip