What is worktree AGENTS.md?

Repository-specific instructions for Worktree Manager, a Go command-line tool that creates and coordinates Git worktrees across multiple projects. A Git worktree is a separate working directory linked to a repository, and these instructions cover ports, Docker instances, and configuration.

Use them when changing the Worktree Manager CLI, its registry or configuration, port allocation, Docker setup, or integrations with coding agents.

They explain how the registry tracks branches, projects, and available ports, so an agent does not break coordination between development instances.

How braunmar/worktree configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to braunmar/worktree. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/braunmar/worktree/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/braunmar/worktree

Made for: Codex, OpenCode.

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/instructions/braunmar/worktree/agents-md/github.svg)](https://agentmods.dev/instructions/braunmar/worktree/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/braunmar/worktree/agents-md"><img src="https://agentmods.dev/badge/instructions/braunmar/worktree/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/braunmar/worktree/agents-md"><img src="https://agentmods.dev/badge/instructions/braunmar/worktree/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,526 This file is loaded in full into every session.

When invoked 4,526 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.

Model	Per session	Once invoked
Fable 5.1	$0.04526	$0.04526
Opus 5.5	$0.01810	$0.01810
Sonnet 5.5	$0.00905	$0.00905
Haiku 4.5	$0.00453	$0.00453

Measured 2mo ago against content hash 4bcd3edfacf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worktree AGENTS.md 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 2mo 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.

AGENTS.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agent when working with code in this repository.

Project Overview

Worktree Manager is a Go CLI tool for managing git worktrees in multi-instance development environments. It creates coordinated worktrees across multiple projects (backend, frontend), allocates ports dynamically, manages Docker instances, and integrates with Claude Code for autonomous development workflows.

Core Architecture

Registry System

Location: pkg/registry/registry.go

The registry is the source of truth for all worktree instances and port allocations:

File: worktrees/.registry.json
Structure: Maps normalized feature names to worktree metadata (branch, ports, projects, compose names)
Port Allocation: Thread-safe allocation from configured ranges
Persistence: Atomic writes with temp file + rename

Key Functions:

Load() - Loads registry from disk, builds port ranges from config
AllocatePorts() - Finds available ports across all configured services
FindAvailablePort() - Checks registry + live port availability (binds to verify)
NormalizeBranchName() - Converts feature/user-auth → feature-user-auth

Configuration System

Location: pkg/config/workconfig.go

Configuration is loaded from .worktree.yml in the project root:

Key Structures:

WorktreeConfig - Main configuration (projects, presets, ports, symlinks, copies)
ProjectConfig - Per-project settings (dir, main_branch, start_command, post_command)
PresetConfig - Groups of projects (e.g., "fullstack" = backend + frontend)
PortConfig - Port/service configuration (name, URL template, port expression, env var)

Port Expression Syntax: Port values support dynamic calculation using {instance} placeholder:

Simple offset: "3000 + {instance}" → 3000, 3001, 3002, ...
Multiplication: "4510 + {instance} * 50" → 4510, 4560, 4610, ...
Static value: "8080" → always 8080

Expression Parsing (parseExpression(), CalculatePort()):

Replace {instance} with actual instance number
Parse expression: base, offset, multiplier
Calculate: base + (offset * multiplier) or base + offset or just base
Validate result is in range 1-65535

Read the full file on GitHub · 514 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.

2mo ago First seen · 514 lines · 4,526 tokens per session scan A 4bcd3edfacf7

Subscribe to this mod's changes

worktree AGENTS.md is an instructions file published in the GitHub repository braunmar/worktree (5 stars, last pushed 2mo ago), licensed MIT. It adds 4,526 tokens to every session, about $0.0181 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.

Git and workflow

worktree AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
worktree AGENTS.mdbraunmar/worktree	Instructions file	5	2mo ago	MIT	A	4,526	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

worktree: Instructions file for Codex