Worktree Cycle Agent Skill

Use for the git worktree lifecycle — starting isolated work and folding it back.

Context cost
7.3k tokensestimated from the bundle, loaded when it triggers
Bundle
6 files · 96.7 kB3 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use for the git worktree lifecycle — starting isolated work and folding it back. START creates a worktree branched from the LOCAL integration branch HEAD (default dev), not the remote default, and asserts the base, and reserves a dev-server port block for it so parallel worktrees do not fight over the same ports. FINISH squash-merges the worktree branch into the local integration branch and cleans up the branch and worktree. Triggers include "워크트리 시작/생성", "워크트리 정리", "dev 로 머지", "squash merge 후 브랜치·워크트리 정리", starting or closing out worktree work. Never pushes.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

developer toolsgit

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md17.6 kB · preview
--- name: worktree-cycle license: MIT compatibility: Bash, git, and Python 3.10+ for coordinated port allocation. Works on Windows through Git Bash. No network access, no push. ---
8# worktree-cycle
9
10Open an isolated git worktree from the local integration branch HEAD, and close it back into
11that branch as a single squash commit. The deterministic git sequence and its guards live in
12the scripts, not in prose. <skill-dir> is the directory holding this file.
13
14Use the user's language when reporting. Report cleanup exactly as it happened — the finish
15script exits non-zero when the worktree or branch could not be removed, and that is a partial
16result, not a success.
17
18## Principles
19
20- **Base is the LOCAL integration branch HEAD.** Branching from the remote default
21 (origin/main, …) drops recent local commits, so the work sits on a stale base and collides
22 at squash-merge time. start branches only from the local HEAD and asserts it immediately
23 after creating the worktree.
24- **Never push.** The merge lands on the local integration branch only. Publishing is a
25 separate human step — the separation matters most in repositories where the integration
26 branch is what actually runs.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,774 words
Files6
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈190
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
7,135
on trigger
The instruction body and 5 supporting files, read only when the skill fires.
3.7%
of a 200k window
Ten skills this size would take about 37% of the window before you open a file.
050k100k150k200k context window

7.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

6 files, 96.7 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to. 1 file of its source is not in the download — listed after these, with why.

  • SKILL.md17.6 kB
  • evals/behavior-evals.json8.9 kB
  • evals/trigger-evals.json2.8 kB
  • scripts/finish-worktree.sh24.7 kB
  • scripts/start-worktree.sh10.5 kB
  • tests/run.sh32.2 kB

Not in the download

Not carried is a type a skill download does not hold. Take it from its source.

  • .gitattributesnot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the download is 6 files — not the whole of its source: 1 file is left out. It is listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Worktree Cycle · 7.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/worktree-cycle/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/worktree-cycle" ] && { [ ! -e .claude/skills/worktree-cycle ] || { mv .claude/skills/worktree-cycle "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/worktree-cycle" .claude/skills/ && echo "Installed .claude/skills/worktree-cycle"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add 555cider/worktree-cycle

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/worktree-cycle/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/worktree-cycle/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/worktree-cycle" ] && { [ ! -e ~/.claude/skills/worktree-cycle ] || { mv ~/.claude/skills/worktree-cycle "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/worktree-cycle" ~/.claude/skills/ && echo "Installed ~/.claude/skills/worktree-cycle" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/worktree-cycle/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 1 file of its source (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Reference555cider/worktree-cycle

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill