using-git-worktrees

A workflow for creating an isolated Git worktree, which is a separate working directory connected to the same Git repository.

In plain words
What is it for?
Use it before implementation work that needs isolation, with checks for existing worktrees and a fallback to Git’s built-in worktree commands.
Why use it?
It keeps feature changes separate from the current checkout, reducing conflicts between tasks and making parallel work safer.

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/skywalkercyt/mp-implement/using-git-worktrees
Any agent
npx skills add skywalkercyt/mp-implement --skill using-git-worktrees
Clone the repo
git clone --depth 1 https://github.com/skywalkercyt/mp-implement

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 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 $0.00041 $0.00697
Opus 5 $0.00020 $0.00349
Sonnet 5 $0.00008 $0.00139
Haiku 4.5 $0.00004 $0.00070

Measured yesterday against content hash 225fcf34d458, 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 yesterday.

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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Git Worktrees

Adapted skill — discipline originating in Superpowers v5.1.0 (MIT, Jesse Vincent), rewritten in mattpocock-skills style. Used by /mp-implement-issue step 3 and both pipelines' Phase 3 to give each slice an isolated workspace.

Isolate the work before touching code: detect existing isolation first, use the harness's native worktree tool if one exists, fall back to git worktree only without one.

1. Detect existing isolation

Run detection before creating anything.

GIT_DIR=$(cd "$(git rev-parse --git-dir)" && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" && pwd -P)
git rev-parse --show-superproject-working-tree 2>/dev/null
  • GIT_DIR != GIT_COMMON and the superproject check prints nothing → already in a linked worktree; skip to setup (step 3). On detached HEAD, note the worktree is externally managed and branch creation happens at finish time.
  • The superproject check prints a path → you're in a submodule; treat it as a normal repo.

In a normal checkout, honor any declared worktree preference without asking. With none declared, ask one consent question; declined → work in place and skip to setup.

2. Create the worktree

Native tool first. If the harness offers one (EnterWorktree-style tool, /worktree command, --worktree flag), use it — it manages placement, branching, and cleanup that the git fallback leaves to you. Then skip to setup.

Git fallback — only with no native tool. Directory priority: declared preference > existing .worktrees/ or worktrees/ (.worktrees/ wins if both) > default .worktrees/ at the repo root.

Verify the directory is git-ignored before creating:

git check-ignore -q <dir> || echo "<dir>/" >> .git/info/exclude
git worktree add .worktrees/<branch> -b <branch>
cd .worktrees/<branch>

A permission error here means the sandbox blocked creation — say so, then run setup and baseline in place.

3. Setup

Auto-detect and install:

[ -f package.json ] && npm install
[ -f Cargo.toml ] && cargo build
[ -f requirements.txt ] && pip install -r requirements.txt
[ -f pyproject.toml ] && poetry install
[ -f go.mod ] && go mod download

Read the full file on GitHub · 69 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. yesterday First seen · 69 lines · 41 tokens per session scan A 225fcf34d458

Subscribe to this mod's changes

using-git-worktrees is a skill published in the GitHub repository skywalkercyt/mp-implement (2 stars, last pushed 29d ago), licensed MIT. It adds 41 tokens to every session and 697 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

software-test-execution

Run scoped tests for a TDD slice, determine the appropriate test framework and command, and report structured pass/fail results. Use when tests need to be executed after writing, implementing, or refactoring code. Reads test metadata, discovers the test framework if needed, executes the scoped test command, parses…

stencila/stencila · 97 tokens

nw-at-completeness-check

Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.

nWave-ai/nWave · 46 tokens

nw-ab-critique-dimensions

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation.

nWave-ai/nWave · 26 tokens

novel-game-analyze

Deconstruct a novel for game adaptation. Compress a raw novel, deconstruction library, or writing project into a SOURCEBIBLE with cited textual evidence, extracting world rules, player verbs, spaces, character will, systems, and visual anchors — without inventing a genre yet. Use for gameable book analysis, analyze a…

zenstory-ai/novel-to-game · 157 tokens

novel-to-game

Turn a novel into a fully playable game on the selected target platform. Orchestrates the whole adaptation pipeline — requirements intake, gameable deconstruction, concept selection, world and visual design, target-runtime build, and evidence-based QA — for a novel in any language. Use for novel to game, story to…

zenstory-ai/novel-to-game · 201 tokens

nw-canary

Canary skill for auto-injection detection.

nWave-ai/nWave · 12 tokens