create-worktree

create-worktree is a cursor rule for Cursor from briangmilnes/APAS-VERUS. It costs 490 tokens per session, scanned A, original, MIT.

A Git worktree rule for creating separate agent workspaces, each with a branch named for the agent and task.

In plain words
What is it for?
It is for creating, switching, and removing agent worktrees using the project’s directory and branch naming conventions.
Why use it?
It keeps parallel coding work isolated so agents can make changes without interfering with one another.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is for creating, switching, and removing agent worktrees using the project’s directory and branch naming conventions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/briangmilnes/apas-verus/create-worktree
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.

Clone the repo
git clone --depth 1 https://github.com/briangmilnes/APAS-VERUS

Made for: Cursor.

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 create-worktree

README.md
[![agentmods](https://agentmods.dev/badge/rules/briangmilnes/apas-verus/create-worktree/github.svg)](https://agentmods.dev/rules/briangmilnes/apas-verus/create-worktree)
Your own site
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/create-worktree"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/create-worktree/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-worktree

Your own site · 80×15
<a href="https://agentmods.dev/rules/briangmilnes/apas-verus/create-worktree"><img src="https://agentmods.dev/badge/rules/briangmilnes/apas-verus/create-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 490 This file is loaded in full into every session.
When invoked 490 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00490 $0.00490
Opus 5.5 $0.00196 $0.00196
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 1mo ago against content hash 2ae7cd957b59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 1mo 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.

.cursor/rules/git/create-worktree.mdc · 59 lines

What it actually says

Create Agent Worktree

Naming convention

Worktree Directory Branch prefix
main ~/projects/APAS-VERUS main
agent1 ~/projects/APAS-VERUS-agent1 agent1/
agent2 ~/projects/APAS-VERUS-agent2 agent2/
agent3 ~/projects/APAS-VERUS-agent3 agent3/

Branch names follow the pattern agentN/<topic> (e.g., agent1/verusify-chap37).

Creating a worktree

# From the main worktree
cd ~/projects/APAS-VERUS

# Create agent1 worktree with a topic branch
git worktree add -b agent1/<topic> ~/projects/APAS-VERUS-agent1 main

# Create agent2 worktree with a topic branch
git worktree add -b agent2/<topic> ~/projects/APAS-VERUS-agent2 main

# Create agent3 worktree with a topic branch
git worktree add -b agent3/<topic> ~/projects/APAS-VERUS-agent3 main

Switching an agent's topic

When an agent finishes a topic and starts a new one, rename the branch — don't recreate the worktree:

# In the agent worktree (e.g., ~/projects/APAS-VERUS-agent1)
git checkout main
git pull origin main
git checkout -b agent1/<new-topic>

Removing a worktree

cd ~/projects/APAS-VERUS
git worktree remove ~/projects/APAS-VERUS-agent1
git branch -d agent1/<topic>

# Similarly for agent2, agent3:
# git worktree remove ~/projects/APAS-VERUS-agent2
# git worktree remove ~/projects/APAS-VERUS-agent3

Rules

  • Each agent works ONLY in its own worktree directory. Never cd into another agent's worktree.
  • Main is the integrator. Agents do not push to main directly.
  • Agents push their own branches: git push origin agent1/<topic>.
  • Main merges agent branches one at a time (see merge-worktree rule).
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. 1mo ago First seen · 59 lines · 490 tokens per session scan A 2ae7cd957b59

Subscribe to this mod's changes

create-worktree is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 23d ago), licensed MIT. It adds 490 tokens to every session, about $0.0020 per session on Opus 5.5. 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.