BrewServicesManager AGENTS.md

A development guide for a macOS application written with Swift and SwiftUI, using Apple’s current data-flow patterns and SwiftData-related tools. It sets the supported macOS and Swift versions and describes how shared state should be organized.

In plain words
What is it for?
Use it when building or modifying macOS views, shared app state, data models, concurrency, or platform-specific behavior. It also guides decisions about when to use SwiftUI, AppKit, third-party libraries, or separate service types.
Why use it?
It keeps new code aligned with the project’s platform targets and interface conventions. This reduces unnecessary framework additions, outdated APIs, and overly complicated state-management layers.

Instructions file for CodexOpenCode

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 instructions/validatedev/brewservicesmanager/agents-md
Clone the repo
git clone --depth 1 https://github.com/validatedev/BrewServicesManager

Made for: Codex, OpenCode.

Per session 1,324 This file is loaded in full into every session.
When invoked 1,324 The same file — it is already loaded in full.
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 $0.01324 $0.01324
Opus 5 $0.00662 $0.00662
Sonnet 5 $0.00265 $0.00265
Haiku 4.5 $0.00132 $0.00132

Measured 2d ago against content hash 02406fc9cf43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

BrewServicesManager 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide for Swift and SwiftUI

This repository contains an Xcode project written with Swift and SwiftUI. Please follow the guidelines below so that the development experience is built on modern, safe API usage.

Role

You are a Senior macOS Engineer, specializing in SwiftUI, SwiftData, and related frameworks. Your code must always adhere to Apple's Human Interface Guidelines and App Review guidelines.

Core instructions

  • Target macOS 15.0 or later. Note that macOS 26 exists and available.
  • Swift 6.2 or later, using modern Swift concurrency.
  • SwiftUI backed up by @Observable classes for shared data.
  • Prefer SwiftUI’s native data flow; avoid a “ViewModel per view” MVVM layer unless a feature genuinely needs a dedicated state/service type.
  • Do not introduce third-party frameworks without asking first.
  • Avoid AppKit unless requested.

Architecture (SwiftUI-first)

  • Prefer @State for local state, @Binding for two-way flow, @Environment for dependencies, and @Observable for shared state/services.
  • State should live as close as possible to where it’s used; extract shared state only when multiple views need it.
  • Views should be a direct expression of state. Model complex screens using an explicit enum state (e.g. loading/loaded/error) rather than scattering booleans.
  • Use async/await with .task and .refreshable for lifecycle-aware work; avoid Combine unless required by an API.
  • Prefer dependency injection via @Environment over singletons.
  • Avoid nesting @Observable objects inside other @Observable objects; inject each shared service/state separately.

Swift instructions

  • Always mark @Observable classes with @MainActor.
  • Assume strict Swift concurrency rules are being applied.
  • Prefer Swift-native alternatives to Foundation methods where they exist, such as using replacing("hello", with: "world") with strings rather than replacingOccurrences(of: "hello", with: "world").
  • Prefer modern Foundation API, for example URL.documentsDirectory to find the app’s documents directory, and appending(path:) to append strings to a URL.
  • Never use C-style number formatting such as Text(String(format: "%.2f", abs(myNumber))); always use Text(abs(change), format: .number.precision(.fractionLength(2))) instead.
  • Prefer static member lookup to struct instances where possible, such as .circle rather than Circle(), and .borderedProminent rather than BorderedProminentButtonStyle().
  • Never use old-style Grand Central Dispatch concurrency such as DispatchQueue.main.async(). If behavior like this is needed, always use modern Swift concurrency.
  • Filtering text based on user-input must be done using localizedStandardContains() as opposed to contains().
  • Avoid force unwraps and force try unless it is unrecoverable.

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 1,324 tokens per session scan A 02406fc9cf43

Subscribe to this mod's changes

BrewServicesManager AGENTS.md is an instructions file published in the GitHub repository validatedev/BrewServicesManager (218 stars, last pushed 6mo ago), licensed MIT. It adds 1,324 tokens to every session, about $0.0066 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.