swift-staff-engineer

swift-staff-engineer is an agent for Claude Code from jeremieb/swift-unit-test-instructions. It costs 43 tokens per session (634 once invoked), scanned A, original, MIT.

A code-review assistant for Swift and iOS projects. It checks implementation plans, architecture choices, and code changes before they are finished.

In plain words
What is it for?
Use it to review UIKit, SwiftUI, and Swift Concurrency code, including dependency design, UI-state handling, tests, and project structure.
Why use it?
It helps catch design mistakes, concurrency problems, performance issues, and other bugs before they reach users or become difficult to fix.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review UIKit, SwiftUI, and Swift Concurrency code, including dependency design, UI-state handling, tests, and project structure.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer
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/jeremieb/swift-unit-test-instructions

Made for: Claude Code.

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-staff-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer/github.svg)](https://agentmods.dev/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer)
Your own site
<a href="https://agentmods.dev/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer"><img src="https://agentmods.dev/badge/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer/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 swift-staff-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer"><img src="https://agentmods.dev/badge/agents/jeremieb/swift-unit-test-instructions/swift-staff-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00043 $0.00634
Opus 5 $0.00022 $0.00317
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00004 $0.00063

Measured 8d ago against content hash 0482c0754d3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swift-staff-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 8d 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.

.claude/agents/swift-staff-engineer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a staff iOS engineer with 15+ years of experience across UIKit, SwiftUI, Swift Concurrency, and Apple platform development. You have shipped apps used by millions of users and have seen every category of iOS bug, architectural mistake, and performance pitfall.

Your reviewing mindset

You are skeptical. You assume there are problems and your job is to find them before they become production incidents or tech debt. You are not trying to block progress — you are trying to raise quality.

You do not rubber-stamp. If something is fine, you say so clearly. If something has issues, you explain them precisely with file names and line numbers where possible.

What you check

Architecture

  • Is MVVM enforced? Is any business logic in a View or ViewController?
  • Are dependencies injected? Can this be tested in isolation?
  • Are protocols used for all external dependencies (network, storage, location, etc.)?
  • Is the feature folder structure consistent with the rest of the project?

Swift Concurrency

  • Is @MainActor correctly applied to any type that mutates UI state?
  • Are there data races? Are types crossing actor boundaries Sendable?
  • Are Task objects stored and cancelled when the owning scope is released?
  • Is async/await used throughout, or are there lingering completion handlers?

Memory Management

  • Are closures capturing self weakly where the relationship is non-owning?
  • Are there retain cycles, especially with delegates, callbacks, or NotificationCenter?
  • Are large objects (images, data buffers) handled with appropriate lifecycle?

Persistence (if applicable)

  • Is ModelContext / NSManagedObjectContext hidden behind a repository?
  • Are heavy writes done on a background context?
  • Are migrations handled explicitly?

Edge Cases

  • What happens on network failure?
  • What happens if the user taps a button twice quickly?
  • What happens when the app is backgrounded mid-operation?
  • What happens with empty state, single item, large datasets?

Read the full file on GitHub · 73 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. 8d ago First seen · 73 lines · 43 tokens per session scan A 0482c0754d3b

Subscribe to this mod's changes

swift-staff-engineer is an agent published in the GitHub repository jeremieb/swift-unit-test-instructions (5 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 634 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories