Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    bix-claude-skills: Claude Code Disk Cleanup

    1

    Scan ~/.claude/, see what is safe to delete, and reclaim disk space with a before/after report.

    Free

    2 usesSecurity scanned
    bix-claude-skills: Claude Code Disk Cleanup

    bix-claude-skills: Claude Code Disk Cleanup

    Example session with this skill installed

    I need to free up some space. Run the cleanup tool to see what I can delete from the Claude directory.

    or run the below commands from claude code.

    /cleanup
    
    Check how much disk space Claude Code is using and clean up the stale stuff.
    
    • Read your context and instructions
    • Compiled the bix-claude-

    Claude Code scanned ~/.claude/ and found 5.94 GB in total, of which 5.50 GB is in directories marked safe to delete. One session is currently running, so its transcript is protected. You selected projects, debug and file-history. The cleanup removed 5.37 GB. Your skills, agents, plugins, settings and memory were not touched.

    Scan output

    DirectorySizeWhat it containsSafe to delete?
    projects/3.12 GBPer-project session transcripts (memory/, CLAUDE.md, active sessions preserved)Yes
    file-history/1.46 GBFile edit history snapshots from past sessionsYes
    debug/788.6 MBDebug log filesYes
    plugins/412.3 MBInstalled plugins and marketplace data (deletion uninstalls them)No (keep)
    telemetry/96.4 MBUsage telemetry cacheYes
    shell-snapshots/31.2 MBShell environment snapshotsYes
    skills/2.1 MBGlobal user-defined skillsNo (keep)
    my-notes/180.0 KBUnknown, investigate before deletingUnknown
    Reclaimable total5.50 GBsum of all rows marked Yesn/a
    ~/.claude/ total5.94 GBall directories aboven/a

    1 active session(s) detected (14.8 MB) and will be preserved.

    Selection (checklist): projects/ (3.12 GB), file-history/ (1.46 GB), debug/ (788.6 MB).

    Report

    DirectoryBeforeAfterSaved
    projects/3.12 GB38.5 MB3.08 GB
    file-history/1.46 GB0 B1.46 GB
    debug/788.6 MB0 B788.6 MB

    Total Memory Saved: 5.31 GB

    ~/.claude/ is now 580.7 MB.

    Next steps

    • Run /cleanup -all next time to clear every safe directory after one confirmation.
    • Check my-notes/, which is not recognized, and decide yourself whether to remove it. The skill never offers to delete unknown directories.
    • Close other Claude Code sessions first if you want their transcripts cleaned too.
    CLAUDE.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    • Scans ~/.claude/ and prints a size table sorted largest first, with each directory marked Yes, No (keep) or Unknown for deletion.
    • Shows a Reclaimable total and a ~/.claude/ total in the table footer.
    • Lets you pick which safe directories to clean, or use -all for one confirmation.
    • Deletes only what you approve, then prints a before/after table with Total Memory Saved.

    Problems it solves

    • ~/.claude/ grows with transcripts, debug logs, file history, caches and snapshots, and it is hard to tell what is safe to remove.
    • Deleting by hand risks wiping skills, agents, settings or memory.
    • Removing a running session's files can break that session.

    How it works

    1. Scan: scan.sh measures every directory, classifies it, detects running sessions by checking each PID, and renders the table.
    2. Select: the agent asks you which safe directories to delete (checklist), or asks one yes/no question with -all.
    3. Delete: delete.sh removes the contents of the chosen directories. A hard blocklist and the classifier refuse anything user-owned.
    4. Report: the script's own before/after table is shown as is.

    All sizes, classification and deletion are done by bundled shell scripts, not by the model, so the numbers are deterministic.

    Why install it

    • Free and open source (Apache-2.0).
    • Nothing is deleted without your confirmation.
    • Protects skills, agents, commands, rules, memory, plugins, settings, credentials and IDE state.
    • No jq or Python needed. Works on macOS, Linux, WSL and Git Bash.

    Requirements

    • Claude Code and bash.
    • A ~/.claude/ directory.

    • Claude Code only. It reads and deletes the ~/.claude/ layout.
    • Deletion is permanent. There is no trash, undo or dry-run mode.
    • The classifier is a fixed list. Directories it does not know are labeled Unknown and are never deleted.
    • Safe directories are emptied entirely, including plans/, todos/, tasks/, backups/ and file-history/. Review the table first if you want anything in them.
    • Running-session detection checks the PID in sessions/*.json. It protects transcripts and session folders in projects/. If you select sessions/, its metadata files are removed along with the rest of that folder.
    • Deletion only touches directories inside ~/.claude/. The scan also reports the size of a Claude Desktop vm_bundles folder, but delete.sh does not remove it.
    • Sizes use du, so figures can differ slightly between macOS, Linux and Git Bash. Output is rounded to one decimal.
    • Requires bash. On Windows use Git Bash, MSYS2, Cygwin or WSL.
    • It will not run on its own. Manual invocation only (/cleanup).

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables

    File Scopes

    ~/.claude/**
    ~/.claude/sessions/*.json
    vm_bundles
    ~/.claude/*/

    Deletion is the purpose of the skill, so it needs shell and file write access, but only inside `~/.claude/` and only for directories you pick. A hard blocklist protects `skills/`, `agents/`, `commands/`, `rules/`, `memory/`, `plugins/`, `ide/`, `scripts/`, `output-styles/`, and files such as `settings.json`, `credentials.json`, `CLAUDE.md`, `.claude.json` and `.mcp.json`. It does not read the contents of credential files.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The cleanup skill is designed specifically for the Claude Code CLI environment, targeting the standard `~/.claude/` directory on Unix-like systems (macOS and Linux). It is not currently compatible with Windows CMD/PowerShell unless using a layer like WSL.

    No, this skill features a strict hard-block list that protects `settings.json`, `credentials.json`, and agent memory. It also checks for active process IDs to ensure it never deletes data from a session you are currently running.

    This skill targets stale debug traces, telemetry logs, and project caches that often bloat over time. By removing these non-essential files, you can reclaim gigabytes of space and improve the performance of your local file system.

    You will receive the core cleanup bash scripts, the integration logic for Claude Code, and a README guide for setup. The purchase includes lifetime access to the current version and any security patches released for this specific skill.

    While there is an `-all` flag for quick bulk cleaning, the skill defaults to a "Scan and Review" mode. This generates a markdown report of disk usage, allowing you to see exactly which directories are safe to delete before you confirm the action.

    Download the zip from Agensi and add the folder to your Claude Code skills directory. You can also install the whole set as a plugin from https://github.com/IamBiswajitSahoo/ClaudeSkills. Then type `/cleanup`.

    Claude Code, bash, and standard tools such as `du`, `grep`, `sed` and `awk`. No jq, Python or network access.

    No. `/cleanup` shows a checklist of safe directories and deletes only the ones you choose. `/cleanup -all` asks one yes/no confirmation first. The model cannot invoke the skill on its own.

    Skills, agents, commands, rules, memory, plugins, IDE state, scripts, output styles, settings, credentials, keybindings, `CLAUDE.md`, `MEMORY.md`, `.claude.json`, `.mcp.json` and `.worktreeinclude`. These are blocked in the script even if passed by name.

    The scan finds running sessions by PID. In `projects/`, their transcripts and working folders are kept, and so are `memory/`, `CLAUDE.md` and `settings*.json`. Only stale session transcripts and folders are removed.

    No. The scripts do the sizing, classification, deletion and report rendering. The model only shows the output and asks the confirmation question.

    Yes. The scan table is shown before any question, with sizes and Safe to delete labels. You can answer the checklist with no selection to stop. There is no separate dry-run mode.

    New in LLM Ops