{{REPO}}-new-worktree

{{REPO}}-new-worktree is a skill for Claude Code from steph-dove/klaussy-agents. It costs 62 tokens per session (443 once invoked), scanned A, a copy of fastapi-new-worktree, MIT.

A Git worktree helper that creates a separate working folder and branch for a task. A worktree lets you work on another branch without switching the files in your current folder.

In plain words
What is it for?
Use it to create task-specific worktrees with suitable branch names, then open the reported folder and start working there.
Why use it?
It removes the repetitive setup involved in starting isolated work while keeping the new branch based on the repository's configured base branch.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the klaussy plugin — 79 skills, 3 hooks, 1 MCP server shipped together

Good fit Use it to create task-specific worktrees with suitable branch names, then open the reported folder and start working there.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/steph-dove/klaussy-agents/new-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.

Any agent
npx skills add steph-dove/klaussy-agents --skill new-worktree
Clone the repo
git clone --depth 1 https://github.com/steph-dove/klaussy-agents

Made for: Claude Code.

Or install klaussy, the plugin that ships this one along with the rest of its 79 skills, 3 hooks, 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 {{REPO}}-new-worktree

README.md
[![agentmods](https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/new-worktree/github.svg)](https://agentmods.dev/skills/steph-dove/klaussy-agents/new-worktree)
Your own site
<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/new-worktree"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/new-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 {{REPO}}-new-worktree

Your own site · 80×15
<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/new-worktree"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/new-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 443 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 88% copy Near-identical to another mod 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 $0.00062 $0.00443
Opus 5 $0.00031 $0.00221
Sonnet 5 $0.00012 $0.00089
Haiku 4.5 $0.00006 $0.00044

Measured 9d ago against content hash 36a64d4f92d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

{{REPO}}-new-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 9d 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.

Origin

This is a copy

88% identical to fastapi-new-worktree — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/klaussy/templates/skills/new-worktree/SKILL.md · 27 lines

What it actually says

Create a new git worktree for the task the user described.

  1. Read CLAUDE.md to understand the project structure and branching conventions.
  2. Create a short, descriptive branch name based on the task (e.g. fix/login-redirect, feat/add-search).
  3. Take the current repository's folder name (you already know the working directory — don't compute it with a shell substitution like $(basename $PWD), which isn't portable to Windows shells), then run git worktree add ../<repo-folder>-<branch-name> -b <branch-name> {{BASE_BRANCH}} to create the worktree from the configured base branch (the trailing start-point keeps the new branch from inheriting whatever branch the user is currently checked out on).
  4. Confirm the worktree was created successfully with git worktree list.
  5. Tell the user the full path to the new worktree so they can open it.

Rules:

  • Always branch from {{BASE_BRANCH}} unless told otherwise.
  • Use lowercase kebab-case for branch names.
  • Prefix with fix/, feat/, chore/, docs/, or refactor/ as appropriate.
  • Do not start work in the worktree — just create it and report the path.

When NOT to use

  • The user just wants a new branch in the current working tree (git checkout -b) — worktrees are for parallel checkouts, not branch creation alone.
  • A worktree for the same branch already exists — surface the existing path; don't create a duplicate.
  • The user is on a non-worktree-friendly hosting setup (some submodule-heavy repos break with worktrees) — flag the risk before creating.
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. 9d ago First seen · 27 lines · 0 tokens per session scan A 36a64d4f92d0

Subscribe to this mod's changes

{{REPO}}-new-worktree is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 443 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to fastapi-new-worktree, differing in 8 lines, and is treated as a copy.