isolated-worktree

isolated-worktree is a skill for Claude Code from abstractonion/cadence. It costs 30 tokens per session (737 once invoked), scanned A, original, MIT.

A workflow for creating a separate Git worktree, which is another working copy of a repository, for parallel or long-running tasks.

In plain words
What is it for?
Use it when multiple agents, pull requests, or lengthy tasks need to work in the same repository at the same time.
Why use it?
It lets work continue in another checkout without changing the branch or files in the main checkout.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the cadence plugin — 38 skills, 15 commands, 5 agents shipped together

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/abstractonion/cadence/isolated-worktree
Any agent
npx skills add abstractonion/cadence --skill isolated-worktree
Clone the repo
git clone --depth 1 https://github.com/abstractonion/cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 38 skills, 15 commands, 5 agents.

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 isolated-worktree

README.md
[![agentmods](https://agentmods.dev/badge/skills/abstractonion/cadence/isolated-worktree.svg)](https://agentmods.dev/skills/abstractonion/cadence/isolated-worktree)
Your own site
<a href="https://agentmods.dev/skills/abstractonion/cadence/isolated-worktree"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/isolated-worktree.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00030 $0.00737
Opus 5 $0.00015 $0.00368
Sonnet 5 $0.00006 $0.00147
Haiku 4.5 $0.00003 $0.00074

Measured 6d ago against content hash 36fa7c3c7d0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

isolated-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 6d 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.

plugins/cadence/skills/isolated-worktree/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Isolated worktree

When parallel agents, PR babysitting, or a long-running task would fight over one checkout, work in a sibling git worktree instead of switching branches in the main tree. The main checkout stays on whatever the user was doing.

Naming patterns

  • PR work: {repo}-pr{N} — sibling directory next to the repo root (e.g. cadence-pr4 beside cadence).
  • Feature branch: {repo}-{branch} with slashes replaced (e.g. cadence-feat-workflow-extensions for feat/workflow-extensions).

Pick one pattern per task and stick to it. Reuse an existing worktree when the branch matches; do not create duplicates.

Create or reuse

  1. Resolve repo root: git rev-parse --show-toplevel.
  2. Check for an existing worktree: git worktree list.
  3. Branch already has a worktree — reuse that path; do not create a duplicate.
  4. Branch only in main checkout (common /own-pr case):
    • User already on the PR branch in main → work in main for that PR, or
    • git worktree add -b {name}-wt ../{name}-wt origin/{branch} — new local branch tracking remote. Push: git push origin HEAD:{branch} (remote branch name, not local -wt name) when push.default=simple.
    • Working tree dirty, branch ambiguous, or neither path applies → stop and ask the user.
    • Do not use git worktree add -f on the same branch for concurrent writes — it conflicts with one-branch-per-worktree.
    • Do not git checkout another branch in the main checkout to free the branch — never switch the user's main tree.
  5. Branch free — add at sibling path: git worktree add ../{name} {branch} (fetch/checkout first if needed).
  6. Confirm git branch --show-current inside the worktree matches intent before editing.

Rules

  • Never disturb the main checkout — do not git checkout the user's branch in the primary tree to do agent work.
  • One branch per worktree — do not point two worktrees at the same branch for concurrent writes.
  • Surgical commits — stage only task-scoped files per clean-commits; push from the worktree when the branch is ready.
  • Clean up when done: git worktree remove ../{name} after the branch is merged or abandoned (confirm with the user if unsure).

Read the full file on GitHub · 53 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. 6d ago First seen · 53 lines · 30 tokens per session scan A 36fa7c3c7d0b

Subscribe to this mod's changes

isolated-worktree is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 737 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens