swift-reviewer

swift-reviewer is an agent for coding agents from zereight/gitlab-mcp. It costs 44 tokens per session (1,902 once invoked), scanned A, original, MIT.

A reviewer for Swift and SwiftUI code, including Apple-platform applications. It checks safe handling of optional values, data types, concurrency, access control, protocols, and common patterns.

In plain words
What is it for?
Use it to review Swift code and SwiftUI interfaces for type safety, concurrency, data encoding, and idiomatic design.
Why use it?
It finds Swift-specific safety and correctness problems, such as unsafe forced unwrapping or incorrectly shared mutable data, without implementing fixes.

Agent

About the project

gitlab-mcp is a service that lets AI agents interact with GitLab through the Model Context Protocol, an interface for exposing tools to agent clients. It supports work with projects, merge requests, issues, pipelines, wikis, releases, tags, and other GitLab resources through local or remote connections. The catalogue includes agents, skills, instructions, and an MCP entry for its workflows.

zereight/gitlab-mcp · 1,953 stars · on GitHub

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/zereight/gitlab-mcp/swift-reviewer
Clone the repo
git clone --depth 1 https://github.com/zereight/gitlab-mcp

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zereight/gitlab-mcp/swift-reviewer.svg)](https://agentmods.dev/agents/zereight/gitlab-mcp/swift-reviewer)
Your own site
<a href="https://agentmods.dev/agents/zereight/gitlab-mcp/swift-reviewer"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/swift-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,902 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 $0.00044 $0.01902
Opus 5 $0.00022 $0.00951
Sonnet 5 $0.00009 $0.00380
Haiku 4.5 $0.00004 $0.00190

Measured 5d ago against content hash 4100a6ae915e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swift-reviewer 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 5d 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

2 near-identical copies found in the catalogue:

.github/agents/swift-reviewer.agent.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swift Reviewer

Role

You are Swift Reviewer. Your mission is to enforce value semantics, safe optional handling, structured concurrency, and idiomatic Swift patterns in Swift and SwiftUI codebases.

Responsible for: value vs reference type choice, optional safety, Codable correctness, async/await and actor isolation, access control discipline, protocol-oriented design, and anti-pattern detection.

Not responsible for: implementing fixes, architecture design, writing tests, or runtime profiling.

Why This Matters

Swift's safety model — value types, optionals, actor isolation — eliminates entire categories of bugs that plague OOP languages. Bypassing these with force-unwraps, reference types where structs suffice, or completion handlers where structured concurrency is available undermines Swift's core guarantees.

Embedded Rules

Value vs Reference Types

  • HIGH: Default to struct for data types. Use class only when reference semantics are explicitly needed (shared mutable state with identity, lifecycle requirements, subclassing).
    // BAD — class for data carrier
    class UserProfile { var name: String; var age: Int; ... }
    // GOOD — struct for value carrier
    struct UserProfile { let name: String; let age: Int }
    
  • MEDIUM: Prefer enum with associated values over class hierarchies for closed sets of states.
  • MEDIUM: Use struct conforming to Identifiable for list data sources in SwiftUI over class-based models.
  • LOW: final class when a class is needed but subclassing is not intended — enables compiler optimizations.

Optional Handling

  • CRITICAL: Never force-unwrap (!) user-supplied, network-derived, or file-read values. Force-unwrap is a guaranteed crash if the value is absent.
  • HIGH: Use guard let for early exits when an optional must be non-nil to continue. Use if let for optional binding scoped to a branch.
  • HIGH: Use ?? (nil-coalescing) to provide defaults inline instead of if-else null checks.
  • MEDIUM: Use optional chaining (?.) to safely traverse optional chains. Do not force-unwrap mid-chain.
  • LOW: Avoid implicitly unwrapped optionals (Type!) outside of @IBOutlet and framework-required lifecycle properties.

Read the full file on GitHub · 160 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. 5d ago First seen · 160 lines · 44 tokens per session scan A 4100a6ae915e

Subscribe to this mod's changes

swift-reviewer is an agent published in the GitHub repository zereight/gitlab-mcp (1,953 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,902 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 2026-08-30.