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 instructions/abhinav503/flutter-agentic/gemini-mdgit clone --depth 1 https://github.com/abhinav503/flutter-agenticWrote 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/instructions/abhinav503/flutter-agentic/gemini-md)<a href="https://agentmods.dev/instructions/abhinav503/flutter-agentic/gemini-md"><img src="https://agentmods.dev/badge/instructions/abhinav503/flutter-agentic/gemini-md.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 | $0.01736 | $0.01736 |
| Opus 5 | $0.00868 | $0.00868 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
flutter-agentic GEMINI.md 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlutterAgentic — Gemini Rules
Full reference →
docs/folder
Monorepo layout
Dart pub-workspace monorepo: one shared core package consumed by multiple Flutter apps.
packages/core/ shared toolbelt → import 'package:core/core/…' (no app-specific code)
apps/jokes/ demo app apps/doc_scanner/ request/response app
apps/ai_chat/ streaming app
One flutter pub get at the repo root resolves all packages. Run make targets from the root; run an app from its folder (apps/<app>). Each app owns its main.dart, di/injection_container.dart, and constants/ (ValueConst/ApiConstants); core holds only CoreConst. The primary feature is always feature/home/.
@docs/ai-rules/conventions.md @docs/reference/architecture.md @docs/explanation/end-goal.md
Read docs/how-to/contributing.md for contributor workflow and git hooks.
Read docs/how-to/add-feature-template.md when scaffolding a new feature — it has the full folder tree, empty class skeletons, DI registration order, and a forbidden-pattern checklist.
Read docs/how-to/add-usecase.md when adding a use case — create the class and register it in injection_container.dart.
Read docs/how-to/design-screen-state.md when designing BLoC events and states — covers business-logic naming, state design, retry context, and screen rendering rules with examples from the jokes feature.
Read docs/how-to/review-code.md when the user asks to review, audit, or check generated code — run through the full checklist and report ✅/❌ per section.
Read docs/how-to/change-app-id.md when the user asks to change the application ID or bundle identifier — covers Android (build.gradle.kts + MainActivity.kt package path) and iOS (project.pbxproj), with Xcode manual steps and provisioning notes.
Read docs/how-to/rename-app.md when the user asks to rename the app — covers display name, package name, and all files that reference the old name.
Read docs/how-to/connect-firebase.md when connecting an app to Firebase — covers checking/installing the Firebase + FlutterFire CLIs, running flutterfire configure, per-app firebase_core, main.dart init, Android Gradle plugin, iOS deployment target (15.0+), and the Xcode GoogleService-Info.plist registration check; it asks which app under apps/ to connect.
Read docs/how-to/add-app-logo.md when setting or changing an app's launcher icon — one brand image (ask the user for it) → every Android/iOS/web size via flutter_launcher_icons, with adaptive-icon safe-zone rules and a per-platform verification checklist.
Read docs/how-to/add-splash-screen.md when adding a native boot splash to an app — flutter_native_splash with theme-derived light/dark colours and a centered logo (4x-density and Android-12 asset rules), plus a verification checklist; pairs with an optional Flutter splash route.
Read docs/how-to/add-notification-feature.md when adding Firebase Cloud Messaging push notifications to an app — covers per-app firebase_messaging + flutter_local_notifications, foreground/background/terminated handling, tap-to-open-a-page routing, and image (rich) notifications, split into shared Flutter code + separate iOS / Android tracks; builds on connect-firebase. Recommend testing FCM on a real Android device (emulator Play services is flaky).
Read docs/explanation/ai-agents.md for per-agent install and usage.
Read docs/tutorials/solid-principles.md to understand how SOLID principles are applied across all layers — useful context when designing new classes or reviewing layer boundaries.
Read docs/tutorials/design-patterns-and-concepts.md for design patterns used in this codebase (Singleton, Repository, DTO, Either, Sealed Classes, Strategy, and more) — explains the why behind structural decisions.
When the user asks to do a release, follow the steps below interactively — ask for confirmation at each step before proceeding.
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.
- 4d ago First seen · 111 lines · 1,736 tokens per session scan A ef2a1fd069ae
flutter-agentic GEMINI.md is an instructions file published in the GitHub repository abhinav503/flutter-agentic (10 stars, last pushed 11d ago), licensed MIT. It adds 1,736 tokens to every session, about $0.0087 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 instructions, from other repositories
flutter_pos CLAUDE.md
Instructions for elrizwiraswara/flutter_pos, covering claude.md - flutter project conventions, architecture, detailed structure, data flow and implementation approach.
intentflow-ios AGENTS.md
Instructions for emrecanozturk/intentflow-ios, covering agent instructions, read first, architecture rules, commands and token budget.
intentflow-ios GEMINI.md
Instructions for emrecanozturk/intentflow-ios, covering gemini cli instructions, context loading, architecture rules and verification.
intentflow-ios intentflow-swift.instructions.md
Instructions for emrecanozturk/intentflow-ios, a project described as: Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.
intentflow-ios intentflow-docs.instructions.md
Instructions for emrecanozturk/intentflow-ios, a project described as: Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.
android-clean-template AGENTS.md
AGENTS.md instructions for mykola-kichatov/android-clean-template, covering agents.md, fresh clone?, build & development commands, architecture and domain layer.