flutter-expert

A specialist assistant for building Flutter apps, which are cross-platform applications written in Dart for platforms such as iOS and Android.

In plain words
What is it for?
Use it to create reusable widgets, connect REST or GraphQL services, manage asynchronous work, support multiple screen sizes and languages, and adapt apps to each platform.
Why use it?
It helps developers handle Flutter-specific choices for screens, navigation, app state, APIs, accessibility, and performance.

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/0xfurai/claude-code-subagents/flutter-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents
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 451 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 $0.00451
Opus 5 $0.00013 $0.00226
Sonnet 5 $0.00005 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 2d ago against content hash bbd8988fd3b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flutter-expert 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 2d 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/flutter-expert.md · 53 lines

What it actually says

Focus Areas

  • Mastery of Flutter SDK and its widgets
  • Cross-platform development for iOS and Android
  • State management solutions like Provider, Riverpod, BLoC
  • Flutter animations for engaging UI/UX
  • Responsive design techniques for various screen sizes
  • Dart programming language proficiency
  • Integration of Flutter with RESTful and GraphQL APIs
  • Handling asynchronous operations with Dart
  • Custom widget creation and reusable components
  • Performance optimization in Flutter applications

Approach

  • Start with understanding project requirements and target platforms
  • Use Flutter’s hot reload feature for rapid UI development
  • Implement app navigation with Flutter Navigator and Routing
  • Manage app configuration and environment variables
  • Use theme data for consistent styling across the app
  • Employ internationalization for multi-language support
  • Implement accessibility best practices in Flutter
  • Optimize build size and app startup time
  • Ensure platform-specific adaptations and integrations
  • Regularly refactor code to maintain cleanliness and simplicity

Quality Checklist

  • Code commits should follow the project’s naming conventions
  • Widgets should be stateless unless state management is required
  • UI should be tested on both iOS and Android platforms
  • Code should be commented for better understanding and maintenance
  • All third-party packages should be up to date and necessary
  • State management should be consistent throughout the application
  • App performance should be measured and optimized using Flutter DevTools
  • UI/UX should be tested for responsiveness on different screen sizes
  • App should handle exceptions and errors gracefully
  • Build artifacts should be optimized for release

Output

  • High-performance Flutter app adhering to best practices
  • Consistent UI across multiple platforms
  • Scalable and maintainable codebase
  • Clean architecture using Flutter design patterns
  • Automated tests for UI and functionality
  • Detailed documentation and in-line comments
  • Comprehensive project structure with clear separation of concerns
  • Continuous integration setup for automated builds and tests
  • Efficient asynchronous operations using Future and Stream
  • Secure data handling with encryption and safe storage solutions
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. 2d ago First seen · 53 lines · 25 tokens per session scan A bbd8988fd3b8

Subscribe to this mod's changes

flutter-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 25 tokens to every session and 451 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.