sweep-worktrees

A cleanup tool for abandoned Git worktrees and their branches. A Git worktree is an extra working folder connected to the same repository, and a zombie worktree is one that remains after normal cleanup failed.

In plain words
What is it for?
Use it to scan for old linked worktrees, find untracked orphan folders, preview cleanup, and remove eligible worktrees and their branches.
Why use it?
It removes stale folders and branches that can clutter a repository or prevent new worktrees from being created. It can preview what would be removed before cleanup.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nirecom/agents/sweep-worktrees
Any agent
npx skills add nirecom/agents --skill sweep-worktrees
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 775 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00775
Opus 5 $0.00016 $0.00387
Sonnet 5 $0.00007 $0.00155
Haiku 4.5 $0.00003 $0.00077

Measured 2d ago against content hash 6210bf857ba9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sweep-worktrees scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`git worktree remove` (if still registered) or `rm -rf` (if not registered
skills/sweep-worktrees/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reclaims zombie linked worktrees left behind when /worktree-end could not physically remove a worktree (e.g. Windows CWD lock from VS Code's extension host). After successful worktree removal, also deletes the corresponding branch. Also scans WORKTREE_BASE_DIR for orphan directories not tracked by git's worktree registry.

Procedure

SWT-1. Resolve $AGENTS_CONFIG_DIR from the environment; abort with a clear error if unset. SWT-2. Invoke the sweeper script (no flag = deletes; --dry-run = preview):

bash "$AGENTS_CONFIG_DIR/bin/sweep-worktrees.sh" [--dry-run] [--min-age-hours N] [--ci-mode]

SWT-3. Print the script's stdout verbatim. Do not summarize or filter.

Forward the user's flags verbatim. Add no flags of your own.

Rules

  • Deletes by default; --dry-run must be explicit to preview only.
  • --force is not supported; the script uses git worktree remove without --force.
  • EPERM / busy / not-empty failures on a per-worktree basis are non-fatal: warning printed, that worktree skipped, sweep continues.
  • Branch deletion (git branch -D) is authorized only AFTER the worktree is removed (git's cascade rule blocks branch deletion while the worktree is registered).
  • Detached HEAD worktrees are skipped with a warning (no branch ⇒ no PR merged check, no branch -D target).
  • A 4-AND safety check is required before any deletion: registered linked worktree AND PR merged AND clean working tree AND mtime > threshold.
  • Orphan-directory scan uses a 4-AND gate: containment under WORKTREE_BASE_DIR AND no .git AND mtime > threshold AND ownership proof via Main repo: field in WORKTREE_NOTES.md. Basename match alone is NOT ownership proof — two unrelated repos can share agents/dotfiles basenames. The former "empty-or-notes-only" gate was removed: a partial git worktree remove can leave a full checkout without a .git file, which is safe to delete when ownership is proven.

Migration notes for #503

Pre-#503 state that this skill no longer reclaims (acceptable one-time cleanup cost; this skill stays safe by refusing to act on it):

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 66 lines · 33 tokens per session scan C 6210bf857ba9

Subscribe to this mod's changes

sweep-worktrees is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 775 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens