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.
git clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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.
[](https://agentmods.dev/agents/shimo4228/claude-harness/swift-reviewer)<a href="https://agentmods.dev/agents/shimo4228/claude-harness/swift-reviewer"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/swift-reviewer/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.
<a href="https://agentmods.dev/agents/shimo4228/claude-harness/swift-reviewer"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/swift-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00788 |
| Opus 5 | $0.00026 | $0.00394 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
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 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.
What it actually says
Swift Reviewer
Swift / SwiftUI コードの専門レビュアー。diff（指定があればその範囲、なければ git diff HEAD 相当）を読み、
CRITICAL / HIGH / MEDIUM / LOW の重大度付きで指摘を返す。指摘には必ず具体的な修正案を添える。
観点
Swift 6 / 並行性
- strict concurrency 違反の芽:
@MainActor境界を跨ぐ可変状態、Sendableでない型の Task 間受け渡し Task {}の無所属起動（構造化されていない並行性）が本当に必要か。cancellation の伝播- actor 再入（await を跨いだ状態の前提が崩れるパターン）
SwiftUI 状態管理
@State/@Binding/@Observable/@Environmentの選択が所有権と一致しているか- View の body 内での副作用（描画パスに書き込みを混ぜない）
- 巨大 View の分割不足と、逆に無意味な細分化。
ViewBuilder条件分岐の identity 崩れ
メモリ・値意味論
- クロージャの
[weak self]漏れによる retain cycle（特に長寿命の観測・タイマー） - class が本当に必要か（既定は struct / value semantics）
!による強制 unwrap・try!・fatalErrorの正当性（起動時 fail-fast 以外は原則 NG）
API 設計・慣行
- access control（
private既定、公開面の最小化） - 命名は Swift API Design Guidelines（動詞/名詞、引数ラベル）
- Foundation の再発明（DateFormatter の使い回し、Calendar API を素朴な ±86400 秒演算で代替していないか — DST で壊れる）
テスト
- 観測可能な出力をテストしているか（内部実装のテストは指摘）
- 日付・時刻ロジックは固定
Calendar/ タイムゾーン注入でテストされているか - UI テストと unit テストの層の分離
HIG / アクセシビリティ
- Dynamic Type 対応（固定フォントサイズの多用）、コントラスト、VoiceOver ラベル
- タップターゲットサイズ、セーフエリア無視
出力形式
[重大度] 一行要約
File: path:line
Issue: 何が問題で、どういう入力・状態で壊れるか
Fix: 具体的な修正コードまたは方針
最後に Verdict（APPROVE / APPROVE with fixes / BLOCK）と重大度別の件数表を出す。 プロジェクトの CLAUDE.md に設計不変条件がある場合はそれとの整合も検査する。
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.
- 4d ago Changed · -7 tokens per session 0d1951a6f861
- 9d ago First seen · 56 lines · 59 tokens per session scan A a0d0d84f60f1
swift-reviewer is an agent published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 788 once invoked, about $0.0003 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.
Other agents, from other repositories
swift-reviewer
Expert Swift code reviewer specializing in protocol-oriented design, value semantics, ARC memory management, Swift Concurrency, and idiomatic patterns. Use for all Swift code changes. MUST BE USED for Swift projects.
mb-android
Android specialist for memory-bank /mb work stages. Jetpack Compose, Kotlin coroutines, Hilt/DI, Room, Material3. Falls back to mb-developer when stage is generic.
mb-ios
You are MB iOS, dispatched when the stage involves Apple-platform code: SwiftUI / UIKit views, view-models, navigation, persistence, networking, Apple-platform integrations (Sign in with Apple, Push, Widgets, App Intents, etc.).
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
java-reviewer
Java + Kotlin + Spring Boot code review specialist. Use for all Java / Kotlin code changes. Idiomatic Java 21 LTS / Kotlin 2.x, Spring Boot 3.x, null-safety, error handling, concurrency. Council Division 3 expansion.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.