Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/abhinav503/flutter-agenticnpx agentmods add rules/abhinav503/flutter-agentic/add-feature-templateWrote 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/abhinav503/flutter-agentic/add-feature-template)<a href="https://agentmods.dev/rules/abhinav503/flutter-agentic/add-feature-template"><img src="https://agentmods.dev/badge/rules/abhinav503/flutter-agentic/add-feature-template/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/abhinav503/flutter-agentic/add-feature-template"><img src="https://agentmods.dev/badge/rules/abhinav503/flutter-agentic/add-feature-template.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 | $0.00015 | $0.01752 |
| Opus 5.5 | $0.00006 | $0.00701 |
| Sonnet 5.5 | $0.00003 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
add-feature-template 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If the feature name was not provided, ask:
"What is the feature name? (e.g. products, auth, settings)"
{Feature} = PascalCase · {feature} = snake_case · {Action} = PascalCase verb · {action} = snake_case verb (e.g. GetProducts / get_products)
Scaffold only — do NOT create entity, model, or use case files.
BLoCs are never registered in GetIt.
Imports: core types -> package:core/core/...; app-level di/constants -> package:{app}/...; same-feature files -> relative. Never the old single-app package:flutter_agentic/....
Run make gen and make analyze at the end before reporting done.
1. Folder tree
mkdir -p apps/{app}/lib/feature/{feature}/data/data_source
mkdir -p apps/{app}/lib/feature/{feature}/data/models
mkdir -p apps/{app}/lib/feature/{feature}/data/repository_impl
mkdir -p apps/{app}/lib/feature/{feature}/domain/entities
mkdir -p apps/{app}/lib/feature/{feature}/domain/repository
mkdir -p apps/{app}/lib/feature/{feature}/domain/usecase
mkdir -p apps/{app}/lib/feature/{feature}/presentation/bloc
mkdir -p apps/{app}/lib/feature/{feature}/presentation/view
mkdir -p apps/{app}/lib/feature/{feature}/presentation/widgets
2. Domain — repository interface
apps/{app}/lib/feature/{feature}/domain/repository/{feature}_repository.dart
abstract interface class {Feature}Repository {}
3. Data — remote data source
{feature}_remote_data_source.dart
abstract interface class {Feature}RemoteDataSource {}
{feature}_remote_data_source_impl.dart
import '{feature}_remote_data_source.dart';
// const no-arg; reaches the network via HttpService.instance (from core),
// e.g. HttpService.instance.get<Map<String, dynamic>>(ApiConstants.someUrl).
class {Feature}RemoteDataSourceImpl implements {Feature}RemoteDataSource {
const {Feature}RemoteDataSourceImpl();
}
4. Data — repository impl
apps/{app}/lib/feature/{feature}/data/repository_impl/{feature}_repository_impl.dart
import 'package:core/core/base/base_repository.dart';
import '../../domain/repository/{feature}_repository.dart';
import '../data_source/{feature}_remote_data_source.dart';
class {Feature}RepositoryImpl with BaseRepository implements {Feature}Repository {
final {Feature}RemoteDataSource _dataSource;
const {Feature}RepositoryImpl(this._dataSource);
}
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 · 220 lines · 15 tokens per session scan A 85310b94ea14
add-feature-template is a cursor rule published in the GitHub repository abhinav503/flutter-agentic (10 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,752 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
flutter
Flutter and coding-agent rules for flutter-agentic-starter.
intentflow
IntentFlow architecture rules for iOS features.
flutter-app
Convenções do app Flutter (lib/).
nativescript
NativeScript best practices and patterns for mobile applications.
gradle
Enforce modern Gradle build practices for Java and Android projects, focusing on Kotlin DSL, modularity, version catalogs, and performance optimizations.
android-networking-retrofit-okhttp
Build Android networking stacks with Retrofit, OkHttp, interceptors, API contracts, and resilient error handling.