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.
npx agentmods add skills/etr/groundwork/use-git-worktreenpx skills add etr/groundwork --skill use-git-worktreegit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.00034 | $0.01544 |
| Opus 5 | $0.00017 | $0.00772 |
| Sonnet 5 | $0.00007 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
use-git-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 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Management
Create and manage isolated git worktrees for task execution with automatic project setup and merge handling.
Overview
Git worktrees provide complete isolation for task work:
- Changes don't affect main workspace until merge
- Can switch between tasks without stashing
- Clean baseline for each task
- Safe to experiment
Workflow
Step 1: Determine Worktree Directory
Find or create the worktree directory using this priority order:
-
Check for existing directory:
# Preferred (hidden, less clutter) ls -d .worktrees 2>/dev/null # Alternative ls -d worktrees 2>/dev/null -
Check CLAUDE.md for directive:
worktree-dir: path/to/worktrees -
Check README.md for configuration: Look for worktree or development setup instructions.
-
Ask user if not found:
"Where should I create worktrees for isolated task work?
.worktrees/(Recommended - hidden, less clutter)worktrees/- Custom location"
Step 2: Verify Directory is Gitignored
Critical: Ensure the worktree directory won't be committed.
git check-ignore -q <worktree-dir>
If not ignored:
- Add to
.gitignorewith user confirmation - Report the change
echo "<worktree-dir>/" >> .gitignore
Step 3: Create Branch and Worktree
Determine branch name from task:
- Input:
TASK-004or4 - Branch:
task/TASK-004 - Worktree path:
<dir>/TASK-004
Create from current HEAD:
# Get current branch as base
BASE_BRANCH=$(git branch --show-current)
# Create branch and worktree in one command
git worktree add -b task/TASK-NNN <dir>/TASK-NNN
Record context:
- Base branch (for later merge)
- Worktree path
- Task ID
Step 4: Auto-Detect and Run Project Setup
Change to worktree directory and detect project type:
| File Present | Setup Command |
|---|---|
package.json |
npm install or yarn install |
Cargo.toml |
cargo build |
requirements.txt |
pip install -r requirements.txt |
Pipfile |
pipenv install |
pyproject.toml |
pip install -e . or poetry install |
go.mod |
go mod download |
Gemfile |
bundle install |
pom.xml |
mvn install |
build.gradle |
./gradlew build |
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.
- yesterday First seen · 256 lines · 34 tokens per session scan A 71a191105c97
use-git-worktree is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 1,544 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…