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/Arenukvern/mcp_flutterWrote 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/rules/arenukvern/mcp_flutter/flutter_ui_dev)<a href="https://agentmods.dev/rules/arenukvern/mcp_flutter/flutter_ui_dev"><img src="https://agentmods.dev/badge/rules/arenukvern/mcp_flutter/flutter_ui_dev/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/rules/arenukvern/mcp_flutter/flutter_ui_dev"><img src="https://agentmods.dev/badge/rules/arenukvern/mcp_flutter/flutter_ui_dev.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 | $0.00008 | $0.00435 |
| Opus 5.5 | $0.00003 | $0.00174 |
| Sonnet 5.5 | $0.00002 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
flutter_ui_dev 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 1mo 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
Flutter widgets and concepts:
- Dart 3.11 syntax for null safety, pattern matching, and more
- Appropriate use of StatelessWidget, or Stateful widgets (NO riverpod)
- Custom reusable widgets (use ui_kit) instead of methods
- Cupertino or Material Design as appropriate
- Proper error handling and async/await for asynchronous operations
- flutter_animate for animations
Widget Composition Guidelines:
-
Appropriate Widget Granularity:
- Prefer fewer, more cohesive widgets over many tiny widgets
- Extract new widget classes only when they are:
- Reused in multiple places
- Complex enough to warrant separation (>10 lines)
- Logically independent with clear boundaries
- For simpler UIs, use a single widget with well-commented sections
-
Code Organization Hierarchy:
- First preference: Use comments to separate logical sections within a widget
- Second preference: Extract logical methods for complex sections (>10 && <30 lines)
- Last preference: Create new widget classes
-
Comment-Based Structure:
- Use section comments to delineate logical UI parts:
// Header section Column( children: [ // Title Text('Title'), // Subtitle Text('Subtitle'), ], ), -
Refactoring Decision Tree:
- Is the component reused? → Extract widget
- Is the component >50 lines? → Consider extraction
- Is the component logically independent? → Consider extraction
- Otherwise → Keep in parent with comments
-
Performance Considerations:
- Be mindful that each widget adds overhead
- Prefer fewer widgets for simpler screens
- Use const constructors aggressively
-
Documentation Balance:
- For single-class approaches, use inline comments instead of class-level docs
- Reserve detailed documentation for public APIs and complex widgets
- Document the "why" more than the "what" when using comments
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.
- 1mo ago First seen · 60 lines · 8 tokens per session scan A bc492b56eee1
flutter_ui_dev is a cursor rule published in the GitHub repository Arenukvern/mcp_flutter (389 stars, last pushed 5d ago), licensed MIT. It adds 8 tokens to every session and 435 once invoked, about $0.0000 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.
Other cursor rules, from other repositories
flutter-app
Convenções do app Flutter (lib/).
best-practices
Flutter Best Practices - enforces current patterns when working with Flutter code.
create-view
Step-by-step guide to create a new MasterFabric view with State, Cubit, and MasterViewCubit.
create-base-widget
How to create base/reusable widgets in MasterFabric - StatelessWidget patterns, composition, layout.
create-config
Configure app via appconfig.json - AssetConfigHelper, nested keys, MasterApp.runBefore.
platform-channels
Native iOS/Android integration via platform channels - no Dart packages, MethodChannel.