Find disk space and Git clutter left by AI coding work, including old worktrees, merged branches, build artifacts, caches, archives, and session logs. Review a scan plan, confirm selected items, then remove only items that remain eligible when checked again.
Reclaim disk space and prune branches left behind by AI coding agents - merged or abandoned git worktrees, merged branches, stale build artifacts (node_modules, .venv, target), old archives and backups, package caches, and old agent session logs. Use when the user runs /cleanup, says the disk is full, or asks to clean up worktrees, branches, or storage.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Free disk space and prune branches with one scan, one confirmation, and one apply. Every deletion goes through scripts/agent_cleanup.py in this skill's directory. Right before acting, it re-checks each git item, artifact folder, archive and the trash, and skips anything that changed since the scan.
Choose what to scan:
--root. The scan covers this repo, the agent worktree folders (Codex, Cursor, Conductor, Vibe Kanban), package caches, agent logs and the trash.--root <dir> for each folder that holds their projects. Look for the usual ones (~/code, ~/dev, ~/src, ~/projects, ~/repos, ~/Developer, ~/Documents/*). If none of them exist, ask the user.Narrow with --only git,artifacts,archives,caches,agents,trash when the user asks for one kind, e.g. "just branches" → --only git. Add --remote only when the user wants merged branches deleted on origin too.
Done when the scan command is chosen.
python3 <skill-dir>/scripts/agent_cleanup.py scan --fetch [--root DIR ...] [--only ...] [--remote]
The scan is read-only, apart from --fetch updating remote-tracking refs. It prints numbered items in four classes and saves the plan:
REMOVE: merged into the base branch, regenerable, or a worktree whose directory is already gone (unregistering it keeps its branch).NEEDS-DECISION: holds something unique (uncommitted or ignored files, unmerged or unpushed commits, build output, archives, old logs).KEEP-ACTIVE and SKIP: open PRs, recent work, long-lived branches, the main checkout, locked or rebasing worktrees, anything a running process is inside, unmounted drives. Never act on these.--help lists the thresholds (--stale-days, --keep-days, --min-size).
Done when the plan is printed with its reclaimable total.
Ask once, using your multi-select question tool if you have one, otherwise a single message, then wait for the answer:
--remote was used, as a separate question: deleting them affects everyone using the repo.KEEP-ACTIVE and SKIP get one summary line so the user knows they were seen.
Done when the user has answered.
Pass exactly the ids the user picked:
python3 <skill-dir>/scripts/agent_cleanup.py apply 1 2 5 9-14
Add --remote only when the picked ids include remote branches the user approved in their own question. apply --recommended takes every REMOVE item; use it only when the user approved all of them and nothing else.
apply prints one line per item: done, skipped (changed since the scan, gone, or now in use), refused, or failed with git's reason. Report each one as printed. Leave skipped and refused items in place; the next scan classifies them again. If the plan is more than 24 hours old, apply refuses it: scan again and confirm again.
git worktree remove refuses a worktree with uncommitted changes. Add --force only for ids where the user explicitly accepted losing those changes. A detached worktree's unique commits are saved under refs/agent-cleanup/ before removal.
Done when every picked id has a result line.
Tell the user:
agent-data item, the agent's built-in retention setting named in its note, so the logs stop piling up.Every action is logged to ~/.local/state/agent-cleanup/history.jsonl.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.
Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.
Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.
Establish rules for when an AI agent should recall past context and save lasting decisions, corrections, preferences, and failures. Works with Markdown files or memory services, preserving decision history and surfacing conflicting records.
Audit local AI coding-agent sessions with agenttrace to identify spending, token use, tool failures, and operational problems. Produce readable or structured reports and define pass-or-fail thresholds for automated continuous integration checks.
Audit saved agent sessions for access to private files and evidence that secret values entered an agent's context. Get findings without displaying secrets, identify keys needing rotation, and inspect Claude Code or Codex sessions in a local report.