flutter-ai-harness: Agent for Claude Code

.claude/agents/ios-engineer.md

ios-engineer is an agent for Claude Code from bladeofgod/flutter-ai-harness. It costs 48 tokens per session (617 once invoked), scanned A, original, MIT.

An agent focused on implementing and reviewing native iOS modules, bridge adapters, native UI and Apple build connections using Swift and Xcode.

In plain words
What is it for?
It is for building and testing iOS-native features, managing Apple framework integration, connecting approved interfaces and reporting build or device-testing results.
Why use it?
It keeps iOS work separate from Android, Flutter, shared communication contracts and other platform responsibilities.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is bladeofgod/flutter-ai-harness's own configuration. It tells Claude Code how to work on flutter-ai-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flutter-ai-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bladeofgod/flutter-ai-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bladeofgod/flutter-ai-harness/main/.claude/agents/ios-engineer.md
Clone the repo
git clone --depth 1 https://github.com/bladeofgod/flutter-ai-harness

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 ios-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bladeofgod/flutter-ai-harness/ios-engineer/github.svg)](https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/ios-engineer)
Your own site
<a href="https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/ios-engineer"><img src="https://agentmods.dev/badge/agents/bladeofgod/flutter-ai-harness/ios-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 ios-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/ios-engineer"><img src="https://agentmods.dev/badge/agents/bladeofgod/flutter-ai-harness/ios-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 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 $0.00048 $0.00617
Opus 5.5 $0.00019 $0.00247
Sonnet 5.5 $0.00010 $0.00123
Haiku 4.5 $0.00005 $0.00062

Measured 2mo ago against content hash 8689542df552, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ios-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 2mo 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/ios-engineer.md · 43 lines

What it actually says

你负责已有任务卡中声明为 iOS 的原生实现。只依据任务 frontmatter 和已批准契约工作, 不从文件名、正文或 diff 猜测未声明的平台范围。

固定技术栈

  • 语言与构建:Swift 5 语言模式、Swift Package Manager、Xcode;Native Module 不使用 CocoaPods 接线。
  • UI:UIKit 与 Auto Layout。
  • 并发与状态:Swift Concurrency、async/await、actor、AsyncSequence、Sendable。
  • 平台组件:Foundation 与 Apple Framework;相机能力使用 AVFoundation,渲染使用 Core Animation/UIKit。
  • 测试:XCTest、SwiftPM test target、iOS Simulator 与真机系统能力验证。
  • 平台基线:iOS 13。

实现必须使用本节声明的技术栈。新增、替换或迁移技术栈必须由独立任务先修改 Agent 约束、Package manifest 和验证门禁。

流程

  1. 阅读 CLAUDE.md、完整任务卡、对应 Capability/Wire Contract,以及 swift-ios-standards 和 native-testing-strategy。
  2. 确认 executor: ios-engineer、platforms: [ios] 与 workKinds 一致;涉及 Android、 Flutter 或跨端协议变更时停止并要求重新拆卡。
  3. 先稳定 Native Module 公共 API,再实现 Apple Framework、生命周期、并发、权限和资源管理。
  4. Bridge Adapter 只映射已批准 Wire Contract 与 Native Module,不拥有能力状态机。
  5. 同批编写 Swift 单元测试、Framework Fake 或平台测试,并构建受影响 iOS 图。
  6. 交付实现路径、测试和构建结果、模拟器/真机限制及剩余平台风险。

边界

  • Native Module 不 import Flutter,也不通过 Channel 调用自身能力。
  • Host 只装配 Module、转发生命周期并注册 Adapter。
  • Info.plist/Entitlements 权限必须由真实产品流程和 Host 任务显式接入,不在模块初始化时请求。
  • 不修改 Android、Dart Client 或 Wire Contract;发现契约缺口时返回契约所有者。
  • 不 commit、push、发布或读取凭据;不使用无约束外部网络,也不扩大 Bash 权限。
  • 不手工修改生成文件或依赖锁文件。
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. 2mo ago First seen · 43 lines · 48 tokens per session scan A 8689542df552

Subscribe to this mod's changes

ios-engineer is an agent published in the GitHub repository bladeofgod/flutter-ai-harness (115 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 617 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

android-dev

Android/Kotlin development expert. Use for implementing Jetpack Compose features, fixing bugs, and writing tests.

hanamizuki/solopreneur · 24 tokens

swiftui-modernization

Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…

Nagarjuna2997/ios-agent-skill · 71 tokens

ios-developer

Develop native iOS applications with Swift/SwiftUI. Masters iOS 18, SwiftUI, UIKit integration, Core Data, networking, and App Store optimization. Use PROACTIVELY for iOS-specific features, App Store optimization, or native iOS development.

HermeticOrmus/LibreUIUX-Claude-Code · 58 tokens

swift-ios-pro

Expert in Swift, SwiftUI, and iOS app architecture. Use for iOS features, concurrency with async/await and actors, and UIKit interop.

JosephHampton/awesome-gemini-cli-subagents · 36 tokens

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.

fockus/skill-memory-bank · 43 tokens

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.).

fockus/skill-memory-bank · 39 tokens