What is create-a-worktree?

A tool-specific guide for creating, inspecting, and removing isolated Git worktrees through Worktree Zero. A worktree is another checkout of the same repository, so agents can work in parallel without sharing one mutable checkout.

Use it to create a separate branch and directory for another agent, inspect its runtime, diagnose storage or dependency-sharing issues, and retire the checkout when finished.

It provides a prescribed way to make parallel checkouts while preserving existing changes and controlling dependency sharing. It also gives checks for the pinned tool version and storage usage.

create-a-worktree — Skill for Claude Code and Codex by lonormaly

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 lonormaly/builders-stack --skill create-a-worktree

Clone the repo

git clone --depth 1 https://github.com/lonormaly/builders-stack

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lonormaly/builders-stack/create-a-worktree/github.svg)](https://agentmods.dev/skills/lonormaly/builders-stack/create-a-worktree)

Your own site

<a href="https://agentmods.dev/skills/lonormaly/builders-stack/create-a-worktree"><img src="https://agentmods.dev/badge/skills/lonormaly/builders-stack/create-a-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lonormaly/builders-stack/create-a-worktree"><img src="https://agentmods.dev/badge/skills/lonormaly/builders-stack/create-a-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 526 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.00526
Opus 5.5	$0.00015	$0.00210
Sonnet 5.5	$0.00007	$0.00105
Haiku 4.5	$0.00004	$0.00053

Measured 1mo ago against content hash f126ca0b8ba4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-a-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 1mo 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.

agents/skills/create-a-worktree/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Builders Stack worktree

Use the repository adapter. It keeps project policy in Builders Stack while the generic source and runtime lifecycle comes from the single wt0 binary.

Create

Preserve every existing change in the current checkout.
Confirm ops/dev/wt0.sh --version reports the version pinned in .wt0-version and Bun 1.3.14 is available. The launcher verifies the release checksum before caching the binary.
From the main checkout, run:

ops/dev/worktree.sh <namespaced-branch>

Use the absolute path it prints. Do not call raw git worktree, copy the repo, copy node_modules, or share a complete mutable dependency directory. The wrapper requires copy-on-write source and attaches the verified Bun prepared environment before reporting the checkout ready.

Work and inspect

Start the stack only through the checkout's normal project command.
Use ops/dev/wt0.sh doctor <path> when storage or dependency sharing is in doubt.
Keep the returned branch and path as the runtime identity for later cleanup.
Treat Finder and du as logical size only. Use the Worktree Zero physical receipt when reporting actual disk allocation.

Remove

After the patch is present in origin/main, leave the checkout and run:

ops/dev/worktree.sh --rm <branch>

The adapter refuses dirty source, unknown ignored files, live processes, unmerged patches, and unpreserved merge commits. Never force past a refusal. Use ops/dev/worktree.sh --gc to evaluate finished managed worktrees; it keeps anything that fails the same safety checks. Provenance for these checks isn't tied to the wrapper alone: a worktree created straight through wt0 create or wt0 run (bypassing this wrapper entirely) is just as safely removable — wt0's own fleet record proves ownership in place of the wrapper's marker file. Prefer ops/dev/worktree.sh <branch> above for the extra guardrails (Bun-version floor, prepared environment, worktree cap, free-disk floor), but a bare wt0 create/wt0 run checkout still tears down cleanly through wt0 remove.

Read the full file on GitHub · 55 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.

1mo ago First seen · 55 lines · 37 tokens per session scan A f126ca0b8ba4

Subscribe to this mod's changes

create-a-worktree is a skill published in the GitHub repository lonormaly/builders-stack (42 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 526 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 2026-09-05.

Git and workflow ai-agents better-auth bun drizzle hono monorepo

add-to-project

Add addons, tooling or a workspace package to an existing Better-T-Stack project, such as PWA, Tauri, Starlight or Fumadocs docs, Biome, Oxlint, Ultracite, Husky, Lefthook, Turborepo, Nx, the MCP or Skills addon, or a shared packages/ . Use when the project has a bts.jsonc file and the user wants to extend it or add…

AmanVarshney01/create-better-t-stack · 102 tokens

safe-extraction

Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.

ZaxbyHub/opencode-swarm · 60 tokens

create-a-worktree