What is ac-git-worktree?

A worktree setup helper for Git, which lets one repository have several working folders and branches at once.

It is for creating a ready-to-use worktree, copying or linking shared assets, setting up worker environments, allowing direnv, and making the setup commit.

It removes the manual work of creating a branch, preparing files, configuring the environment, and committing the initial setup.

ac-git-worktree — Skill for Claude Code and Codex by WaterplanAI: A worktree setup helper for Git, which lets one…

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/waterplanai/agentic-config/ac-git-worktree

Any agent

npx skills add WaterplanAI/agentic-config --skill ac-git-worktree

Clone the repo

git clone --depth 1 https://github.com/WaterplanAI/agentic-config

Made for: Claude Code, Codex.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 2 agents, 1 plugin.

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/waterplanai/agentic-config/ac-git-worktree.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-git-worktree)

Your own site

<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-git-worktree"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-git-worktree.svg" alt="Measured on agentmods" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,645 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.

Model	Per session	Once invoked
Fable 5	$0.00050	$0.03645
Opus 5	$0.00025	$0.01822
Sonnet 5	$0.00010	$0.00729
Haiku 4.5	$0.00005	$0.00364

Measured 5d ago against content hash 8759049507fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ac-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 5d 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.

packages/pi-ac-git/skills/ac-git-worktree/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Worktree - pi adaptation

Create a new git worktree with:

serial branch/bootstrap setup using the bundled package scripts
asset wiring from .worktree.yml or bounded inference
shared worker-wave environment setup through subagent
serial direnv allow, commit, and final summary

Current shipped boundary

This pi wrapper now ships, but it stays inside the bounded IT003 contract:

branch/bootstrap is handled directly in this skill; do not try to invoke ac-git-branch from inside the skill
the shared pi-compat worker-wave surface is used only for the environment-setup wave
.worktree.yml discovery, asset wiring, direnv allow, final commit, and final summary stay coordinator-owned
if user input is required, only the coordinator uses AskUserQuestion; workers stay non-interactive

Arguments

worktree_name (required): base name for the branch and worktree
assets_path (optional): explicit path to shared assets to mirror into the worktree

Required references

Read these when needed:

cookbook/setup.md when no .worktree.yml exists or the user wants setup help
../../assets/scripts/spec-resolver.sh for serial branch/spec bootstrap
node_modules/@agentic-config/pi-compat/assets/orchestration/protocol/worker.md for every environment worker
node_modules/@agentic-config/pi-compat/assets/orchestration/tools/write-result.js
node_modules/@agentic-config/pi-compat/assets/orchestration/tools/summarize-results.js

Pre-flight checks

Verify repo root:

REPO_ROOT=$(git rev-parse --show-toplevel)

Verify the main checkout is clean before branch/bootstrap work:
```
git -C "$REPO_ROOT" status --short
```
- If dirty: STOP and ask the user to clean or stash changes first.
Validate worktree_name:
- required
- allow only letters, numbers, -, and _
- reject spaces and shell-special characters

Generate the unique branch/worktree name:

UUID_PREFIX=$(uuidgen | cut -c1-6 | tr 'A-Z' 'a-z')
FULL_NAME="$UUID_PREFIX-<worktree_name>"
WORKTREE_PATH="$REPO_ROOT/trees/$FULL_NAME"

Read the full file on GitHub · 414 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.

cookbook/setup.md 4.0 KB

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.

5d ago First seen · 414 lines · 50 tokens per session scan A 8759049507fa

Subscribe to this mod's changes

ac-git-worktree is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 3,645 once invoked, about $0.0003 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.

Git and workflow agentic ai claude-code config cursor workflow

audit-library-health

Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.

MoizIbnYousaf/Ai-Agent-Skills · 33 tokens

install-from-remote-library

Use when installing skills from a shared ai-agent-skills library repo. Inspect with --list first, prefer --collection, and preview with --dry-run before installing.

MoizIbnYousaf/Ai-Agent-Skills · 44 tokens

share-a-library

Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.

MoizIbnYousaf/Ai-Agent-Skills · 41 tokens

update-installed-skills

Use when syncing or updating previously installed skills to their latest version. Always dry-run updates before applying, and check for breaking changes.

MoizIbnYousaf/Ai-Agent-Skills · 31 tokens

editorial-illustrations

Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent. This is a GENERATIVE GUIDE, not a template gallery: it teaches the "claim -> geometry" method so any session can invent…

huytieu/COG-second-brain · 178 tokens

daily-journal

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…

huytieu/COG-second-brain · 107 tokens