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 skills/aarvion-ai/stackwise-skills/flutter-expertnpx skills add Aarvion-AI/stackwise-skills --skill flutter-expertgit clone --depth 1 https://github.com/Aarvion-AI/stackwise-skillsWrote 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/skills/aarvion-ai/stackwise-skills/flutter-expert)<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/flutter-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/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 5.1 | $0.00128 | $0.02198 |
| Opus 5 | $0.00064 | $0.01099 |
| Sonnet 5 | $0.00026 | $0.00440 |
| Haiku 4.5 | $0.00013 | $0.00220 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Expert
Turns Claude into a senior Flutter engineer who ships idiomatic Dart 3 / Flutter 3.3x code with modern state management, correct navigation, and verified builds - not the 2021-era patterns that dominate training data.
When to Use This Skill
- Building screens, widgets, or features in an existing Flutter app
- Choosing and wiring state management (Riverpod code-gen providers, AsyncNotifier, Bloc/Cubit)
- Navigation with GoRouter: ShellRoute/StatefulShellRoute, auth redirects, deep links
- Diagnosing jank, excessive rebuilds, or slow lists
- Calling native platform code (MethodChannel, Pigeon) or C libraries (dart:ffi)
- Modeling data with freezed + json_serializable and Dart 3 sealed classes/records
- Writing widget tests, golden tests, and integration tests (integration_test, patrol)
- Release prep: flavors, Android signing, iOS provisioning basics
Core Workflow
- Analyze - Read
pubspec.yaml(Flutter/Dart SDK constraints, state-management and router packages, code-gen deps),analysis_options.yaml(lint set), andlib/layout before writing anything. Match the project's existing state-management choice - do not introduce Riverpod into a Bloc app or vice versa. Note whether the project uses code generation (build_runner,freezed,riverpod_generator,go_router_builder). - Implement - Write the change using Dart 3 idioms: sealed classes + exhaustive
switchexpressions, records for lightweight tuples, pattern matching over manual casts,constconstructors everywhere possible. Prefer code-gen providers (@riverpod) over manual ones,StatelessWidget/ConsumerWidgetoverStatefulWidgetunless local ephemeral state is genuinely needed. - Generate code - If the change touches
@riverpod,@freezed,@JsonSerializable, or typed routes, rundart run build_runner build --delete-conflicting-outputs; if generation fails, fix the annotated source and re-run until it completes with no errors. - Verify analyze/format - Run
dart format .thenflutter analyze; fix all reported issues and re-run until clean before proceeding. Treat infos/deprecations (e.g.withOpacity,WillPopScope) as real work items, not noise. - Test - Write or update widget/unit tests for the change, then run
flutter test; fix all failures and re-run until every test passes. For flows spanning navigation or platform channels, add anintegration_test(or patrol) case and run it on a device/emulator:flutter test integration_test; debug and re-run until it passes. - Prove it works - Run the app (
flutter run -d <device>or the project's flavor variant, e.g.flutter run --flavor dev -t lib/main_dev.dart), exercise the changed flow, and check the console for exceptions and layout overflows. For performance work, confirm in DevTools (rebuild stats, frame chart) that the fix actually reduced rebuilds/frame times.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 122 lines · 128 tokens per session scan A b27c4d517959
flutter-expert is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 128 tokens to every session and 2,198 once invoked, about $0.0006 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 skills, from other repositories
audit-ppmplugin
Statically audit a built .ppmplugin before wrap testing. Checks archive layout, manifest compatibility, bundle consistency, Android DEX integrity and SDK leakage, iOS framework structure, native source-to-receiver alignment, and the PCF composite-key/sendAsync transport contract. Reports CRITICAL, WARNING, and INFO…
generate-ppmplugin
Build and verify a third-party .ppmplugin end to end. This recommended entry point detects Android and iOS source, confirms target platforms, then invokes the manifest, platform build, assemble, and audit stages in order. Advanced users can invoke a stage directly for focused reruns or debugging. Produces a…
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
enable-tables-offline
Internal mobile-app workflow read and executed only by /setup-offline-profile to enable Dataverse table prerequisites for a Mobile Offline Profile.
preview-screens
Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.
assemble-ppmplugin
Assemble the final .ppmplugin binary bundle for a PAM native extension and verify its contents. First reconciles the manifest's declared entrypoints against the binaries actually staged — if the manifest declares a platform with no built binary it gates (build it / ship without it / stop) rather than shipping a broken…