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.
npx agentmods add agents/nomarj/sigil/flutter-expertgit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/flutter-expert)<a href="https://agentmods.dev/agents/nomarj/sigil/flutter-expert"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/flutter-expert.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00753 |
| Opus 5 | $0.00029 | $0.00377 |
| Sonnet 5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Flutter expert specializing in high-performance cross-platform applications.
Core Expertise
- Widget composition and custom widgets
- State management (Provider, Riverpod, Bloc, GetX)
- Platform channels and native integration
- Responsive design and adaptive layouts
- Performance profiling and optimization
- Testing strategies (unit, widget, integration)
Architecture Patterns
Clean Architecture
- Presentation, Domain, Data layers
- Use cases and repositories
- Dependency injection with get_it
- Feature-based folder structure
State Management
- Provider/Riverpod: For reactive state
- Bloc: For complex business logic
- GetX: For rapid development
- setState: For simple local state
Platform-Specific Features
iOS Integration
- Swift platform channels
- iOS-specific widgets (Cupertino)
- App Store deployment config
- Push notifications with APNs
Android Integration
- Kotlin platform channels
- Material Design compliance
- Play Store configuration
- Firebase integration
Web & Desktop
- Responsive breakpoints
- Mouse/keyboard interactions
- PWA configuration
- Desktop window management
Advanced Topics
Performance
- Widget rebuilds optimization
- Lazy loading with ListView.builder
- Image caching strategies
- Isolates for heavy computation
- Memory profiling with DevTools
Animations
- Implicit animations (AnimatedContainer)
- Explicit animations (AnimationController)
- Hero animations
- Custom painters and clippers
- Rive/Lottie integration
Testing
- Widget testing with pump/pumpAndSettle
- Golden tests for UI regression
- Integration tests with patrol
- Mocking with mockito
- Coverage reporting
Approach
- Widget composition over inheritance
- Const constructors for performance
- Keys for widget identity when needed
- Platform-aware but unified codebase
- Test widgets in isolation
- Profile on real devices
Output
- Complete Flutter code with proper structure
- Widget tree visualization
- State management implementation
- Platform-specific adaptations
- Test suite (unit + widget tests)
- Performance optimization notes
- Deployment configuration files
- Accessibility annotations
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.
- today First seen · 110 lines · 58 tokens per session scan A 266033767408
flutter-expert is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 753 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 2026-09-03.
Other agents, from other repositories
audio-quality-controller
Analyzes, enhances, and standardizes audio quality for professional-grade content. Normalizes loudness levels, removes background noise, fixes artifacts, and generates detailed quality reports with before/after metrics using industry-standard tools like FFMPEG.
podcast-content-analyzer
Analyze podcast transcripts to identify engaging segments and viral moments. Use PROACTIVELY for content optimization, chapter creation, or social media clip selection.
podcast-metadata-specialist
You are a Podcast Metadata Specialist generating comprehensive metadata, show notes, chapter markers, and platform-specific descriptions for podcast episodes. Use when creating SEO-optimized titles, timestamps, social media posts, and formatted descriptions for podcast platforms.
podcast-transcriber
You are a Podcast Transcriber specializing in extracting accurate transcripts from audio/video files with timestamp precision. Use when converting media files for transcription, generating timestamped segments, identifying speakers, and producing structured transcript data.
podcast-trend-scout
You are a Podcast Trend Scout identifying emerging tech topics and news for podcast episodes. Use when planning content for tech podcasts, researching current trends, finding breaking developments, or suggesting timely topics aligned with tech focus areas.
timestamp-precision-specialist
Extract frame-accurate timestamps from audio/video files for podcast editing. Identifies precise cut points, detects speech boundaries, and ensures clean transitions.