using-git-worktrees

A set of rules for using Git worktrees, which are separate working directories linked to one Git repository. It permits them only when the user or an approved task explicitly authorizes isolation.

In plain words
What is it for?
Use it to decide whether a task may create an isolated worktree and to guide that process when authorization has been given.
Why use it?
It prevents unnecessary worktree creation and makes the conditions for isolating changes clear.

Skill for Claude CodeCodex

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/tx1207/hello-scholar/using-git-worktrees
Any agent
npx skills add Tx1207/hello-scholar --skill using-git-worktrees
Clone the repo
git clone --depth 1 https://github.com/Tx1207/hello-scholar

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,956 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 $0.00043 $0.01956
Opus 5 $0.00022 $0.00978
Sonnet 5 $0.00009 $0.00391
Haiku 4.5 $0.00004 $0.00196

Measured 2d ago against content hash c978f8678383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-git-worktrees 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 2d 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.

skills/using-git-worktrees/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Git Worktrees

Entry Gate

Enter only with one of these explicit authorizations:

  1. Explicit user request: The user clearly asks for a Git worktree or an isolated workspace.
  2. Approved Task requirement: An Approved Task explicitly says to use a Worktree Process.
  3. Approved risk recommendation: The Agent states a concrete isolation risk, such as changing a user-dirty checkout or a branch used by parallel work, and the user explicitly approves the recommendation.

An ordinary Plan, Task, Feature, or Validation label is not authorization. If none applies, return to the current Task flow without running Git commands from this skill. Do not ask about or create a worktree merely because the work is implementation-shaped.

For a concrete risk recommendation that has not yet been approved, state the specific risk and ask whether to prepare an isolated worktree. Wait for an explicit answer. Approval activates authorization 3; a refusal returns to the current Task flow without creation.

An explicit user request, an Approved Task requirement, and an approved risk recommendation already provide creation consent. Do not ask one of these paths for the same consent again.

When authorized, prepare an isolated Git workspace. Core order: Detect existing isolation first -> choose mechanism -> prepare -> verify.

Scope and Exit

This skill ends when an isolated workspace is usable and its baseline status is known. It does not implement the feature, commit, merge, clean up, or remove a worktree.

After this skill exits, follow the current AGENTS and Task requirements for implementation and verification. No-worktree, declined isolation, or a blocked creation never waives required tests. Cleanup requires separate explicit authorization and real provenance for the workspace and branch.

Step 0: Detect Existing Isolation

Run this step only after the Entry Gate authorizes isolation. Before creating anything, capture the repository topology and source-checkout state:

Read the full file on GitHub · 175 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 175 lines · 43 tokens per session scan A c978f8678383

Subscribe to this mod's changes

using-git-worktrees is a skill published in the GitHub repository Tx1207/hello-scholar (5 stars, last pushed 21d ago), licensed MIT. It adds 43 tokens to every session and 1,956 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens