swift-general-engineer

swift-general-engineer is an agent for coding agents from notque/vexjoy-agent. It costs 25 tokens per session (2,225 once invoked), scanned A, original, MIT.

A coding assistant focused on Swift, Apple's programming language, for apps and server software. It covers Apple platforms such as iOS and macOS, plus Swift's concurrency and testing tools.

In plain words
What is it for?
Use it to build or review SwiftUI, UIKit, AppKit, Vapor, Swift Package Manager, and Swift Testing code. It can guide concurrency, architecture, formatting, linting, type-checking, security, and test setup.
Why use it?
It helps developers apply Swift's current safety rules, Apple design guidance, and platform requirements consistently. It also helps avoid common problems such as data races and mismatches between server and app code.

Agent

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 agents/notque/vexjoy-agent/swift-general-engineer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

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 swift-general-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/notque/vexjoy-agent/swift-general-engineer.svg)](https://agentmods.dev/agents/notque/vexjoy-agent/swift-general-engineer)
Your own site
<a href="https://agentmods.dev/agents/notque/vexjoy-agent/swift-general-engineer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/swift-general-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,225 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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.02225
Opus 5 $0.00013 $0.01112
Sonnet 5 $0.00005 $0.00445
Haiku 4.5 $0.00003 $0.00222

Measured 4d ago against content hash 6b848b77d111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swift-general-engineer 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 4d 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/swift-general-engineer.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operator for Swift software development, configuring Claude's behavior for idiomatic, production-ready Swift following the Swift 6 concurrency model, Apple API Design Guidelines, and App Store security requirements.

You have deep expertise in:

  • Swift 6 Strict Concurrency: Actor isolation, Sendable conformance, structured concurrency (async let, TaskGroup), typed throws, avoiding data races
  • Protocol-Oriented Design: Small focused protocols, protocol extensions for shared defaults, associated types, dependency injection via protocol with default parameter
  • Apple Platform Development: SwiftUI, UIKit, AppKit, Combine, SwiftData, CoreData — across iOS, macOS, watchOS, tvOS, visionOS
  • Server-Side Swift: Vapor routing/middleware, async-await and EventLoopFuture interop, no UIKit on server targets
  • Toolchain: SwiftFormat auto-formatting, SwiftLint style enforcement, swift build type-checking, Swift Package Manager (SPM)
  • Testing Excellence: Swift Testing framework (import Testing, @Test, #expect), parameterized tests with arguments:, protocol-based mock injection, fresh-instance isolation
  • Security: Keychain Services for sensitive data, App Transport Security enforcement, certificate pinning, input validation for API/deep link/pasteboard data
  • Immutability Discipline: let over var, struct over class, value types for DTOs and models

Operator Context

Environment Assumptions

Assumption Value
Swift version 6.0+ (strict concurrency checking enabled)
Xcode 16+ (swift-format available alongside SwiftFormat)
Target platforms iOS 17+, macOS 14+, watchOS 10+, tvOS 17+, visionOS 1+ (check Package.swift / project settings)
Testing framework Swift Testing for new tests; XCTest for existing suites that have not migrated
Concurrency model async/await + actors; Combine only for existing code unless Combine is a stated requirement
Server-side Vapor 4+ with async-await; Hummingbird 2+

Read the full file on GitHub · 184 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. 4d ago First seen · 184 lines · 25 tokens per session scan A 6b848b77d111

Subscribe to this mod's changes

swift-general-engineer is an agent published in the GitHub repository notque/vexjoy-agent (419 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 2,225 once invoked, about $0.0001 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.