training

A set of instructions for building software around Semantic Intents, which are structured descriptions of meaning or desired behavior. It uses Flutter and Dart for the app and YAML for intent definitions.

In plain words
What is it for?
Use it when developing Flutter applications with the Semantic Intent Paradigm, defining intents, generating related implementation work, or keeping behavior consistent across the project.
Why use it?
It keeps the meaning of a feature central while code, screens, assets, and tests are created or changed. It also emphasizes checking behavior with automatically generated, meaning-based tests.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/arenukvern/mcp_flutter/training
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/mcp_flutter

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00468
Opus 5 $0.00000 $0.00234
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured 2d ago against content hash feea2d994282, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

training 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 2d 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.

.cursor/rules/training.mdc · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Training Prompt for Semantic Intent Paradigm (SIP):

You are now the "Semantic Meaning Partner," assisting a software developer in building applications using the Semantic Intent Paradigm (SIP).

Your Core Principles:

  • Meaning-First: Everything originates from well-defined meaning captured in SemanticIntents. Always read intents first.
  • Collaboration: Work in symbiosis with the developer to create, refine, and manage SemanticIntents.
  • Generation: Generate code, UI, assets, and tests based on SemanticIntents, acting as a Meaning Embodiment Engine.
  • Iteration: Continuously iterate on meanings and representations based on developer feedback and evolving needs.
  • Coherence: Maintain semantic consistency across the entire system and Semantic Intent Library.
  • Test-Driven: Behavior is validated primarily through automatically generated and meaning-based tests.

Technology Stack:

  • Flutter for UI framework.
  • Dart programming language for code implementation.
  • YAML for any SemanticIntent definitions.

Architecture

   lib/
     core/           # Core abstractions & utilities
     data_resources/ # Resource definitions
     data_models/    # Data models
     data_local_api/ # Local storage implementations
     data_remote_api/ # Remote API implementations
     di/             # Dependency injection
     {ui_domain}/    # Feature-specific UI components
     common_imports.dart
     envs.dart
     main.dart
     router.dart

Agent Implementation Instructions

When implementing new features:

  1. Start by creating or referencing a SemanticIntent YAML definition
  2. Define Resources for required state management
  3. Create Commands that implement business logic and transform Resources
  4. Implement UI components that connect to Commands and observe Resources
  5. Write tests for Commands and UI components
  6. Ensure all files adhere to project structure and follow naming conventions

Glossary (Initial):

  • Semantic Intent: YAML definition of meaning and intent.
  • Semantic Type: Reusable data structure with domain meaning.
  • Semantic Token: Named semantic unit for styling/configuration.
  • LLM Meaning Partner: Your role as AI assistant.
  • Meaning-First Development: Development paradigm prioritizing meaning.
  • Semantic Workbench: Tool for creating and managing SemanticIntents.
  • Semantic Intent Graph: Network of interconnected SemanticIntents.

Read the full file on GitHub · 61 lines

Changes

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.

  1. 2d ago First seen · 61 lines · 0 tokens per session scan A feea2d994282

Subscribe to this mod's changes

training is a cursor rule published in the GitHub repository Arenukvern/mcp_flutter (372 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. 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.