worktree

worktree is a command for Claude Code, OpenCode from permanu/superskill. It costs 14 tokens per session (110 once invoked), scanned A, original, Apache-2.0.

A worktree command for checking and auditing Git worktrees, which are separate working directories linked to branches, and for reclaiming unused space safely.

In plain words
What is it for?
Use it to view status, audit duplicates or leaks, and preview or confirm reversible worktree cleanup.
Why use it?
It helps find duplicate or abandoned worktrees without deleting files, branches, or user data directly.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/.

Part of the superskill plugin — 1 skill, 4 commands, 1 MCP server shipped together

Good fit Use it to view status, audit duplicates or leaks, and preview or confirm reversible worktree cleanup.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/permanu/superskill/worktree
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.

Clone the repo
git clone --depth 1 https://github.com/permanu/superskill

Made for: Claude Code, OpenCode.

Or install superskill, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for worktree

README.md
[![agentmods](https://agentmods.dev/badge/commands/permanu/superskill/worktree/github.svg)](https://agentmods.dev/commands/permanu/superskill/worktree)
Your own site
<a href="https://agentmods.dev/commands/permanu/superskill/worktree"><img src="https://agentmods.dev/badge/commands/permanu/superskill/worktree/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for worktree

Your own site · 80×15
<a href="https://agentmods.dev/commands/permanu/superskill/worktree"><img src="https://agentmods.dev/badge/commands/permanu/superskill/worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 110 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.00110
Opus 5.5 $0.00006 $0.00044
Sonnet 5.5 $0.00003 $0.00022
Haiku 4.5 $0.00001 $0.00011

Measured 10d ago against content hash c6b6abccbe03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worktree scanned grade A with 0 findings 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 10d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/commands/worktree.md · 12 lines

What it actually says

Use the superskill worktree MCP tools. Input: $ARGUMENTS (empty = status).

  • status → worktree_status
  • audit / duplicates / leaks → worktree_audit (read-only)
  • gc / free space → worktree_gc dry-run first; pass confirm=true only after I approve.

Never deletes worktrees, branches, or user files; reclaims are quarantined and reversible.

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. 10d ago First seen · 12 lines · 14 tokens per session scan A c6b6abccbe03

Subscribe to this mod's changes

worktree is a command published in the GitHub repository permanu/superskill (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 110 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.

Related

Other commands, from other repositories

arrange-workspace-flow-choose-workspace-layout

Phase 1 Choose Workspace Layout of arrange-workspace-flow.

griddynamics/rosetta · 22 tokens

taskstoissues

A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.

loulanyue/spec-kit-zh · 24 tokens

ijfw-ship

Run the IJFW workflow Ship phase (Deep D6). Pre-flight, deploy, and close. Usage: /ijfw-ship.

FerroxLabs/ijfw · 32 tokens

branch-commit

Return a branch name and concise commit message (max 3 lines) for the current task, grounded in the real git diff; with --apply, create the commit after showing the staged diff. Use when the user only needs quick branch and commit naming before committing, PR packaging is unnecessary, and a real diff exists; use…

Mozurok/fhorja.dev · 111 tokens

approve-proposed

Atomically persist every file marked PROPOSED in the most recent prior assistant turn's ### Artifact changes block, promoting staged content to real files. Invoked on request only. Use when that block contained files marked PROPOSED and you have accepted the inline content of each. Do not use when the prior turn had…

Mozurok/fhorja.dev · 107 tokens

pr-package

Prepare a GitHub PR delivery package (branch, commits, PR title and body, reviewer notes) from the real git diff against an explicit base branch, persisted as PRPACKAGE.md, never inventing work outside the diff. Use when scope is done and diff is stable. Do not use mid-implementation, for a branch name (use…

Mozurok/fhorja.dev · 109 tokens