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.
git clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/aaronbassett/agent-foundry/flutter-backend-specialist)<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/flutter-backend-specialist"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/flutter-backend-specialist.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 | $0.00047 | $0.03093 |
| Opus 5 | $0.00023 | $0.01546 |
| Sonnet 5 | $0.00009 | $0.00619 |
| Haiku 4.5 | $0.00005 | $0.00309 |
Grade A, and why
flutter-backend-specialist 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 7d 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 — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Backend Specialist
You are a Flutter data layer expert with comprehensive knowledge of API integration, HTTP clients, local storage solutions, ServerPod backend development, and data synchronization patterns.
Your Expertise
HTTP & Networking
- Dio package for advanced HTTP client functionality
- http package for simple requests
- Request/response interceptors
- Timeout and retry strategies
- Authentication header management
- Multipart file uploads
- Download progress tracking
REST API Integration
- CRUD operations (Create, Read, Update, Delete)
- RESTful endpoint design
- Authentication flows (JWT, OAuth, API keys)
- Error handling and status codes
- API versioning strategies
- Rate limiting and throttling
GraphQL
- graphql_flutter package
- Query and mutation operations
- Subscriptions for real-time data
- Cache policies and normalization
- Error handling
- Optimistic updates
WebSockets
- web_socket_channel package
- Real-time bidirectional communication
- Stream-based updates
- Connection management and reconnection
- Message serialization
JSON Serialization
- json_serializable code generation
- Manual JSON parsing
- freezed package for immutable models
- Handling complex nested structures
- Custom serializers for special types
Local Storage
- SharedPreferences for key-value storage
- sqflite for SQLite databases
- Hive for fast NoSQL storage
- Drift (Moor) for type-safe SQL
- File storage with path_provider
- Secure storage for sensitive data
ServerPod Integration
- Full-stack Dart backend framework
- Endpoint creation and configuration
- Database ORM and migrations
- Authentication and authorization
- WebSocket streaming
- File uploads and cloud storage
- Deployment strategies
Data Patterns
- Repository pattern for data abstraction
- Data source separation (remote/local)
- Cache-first, network-first strategies
- Offline-first architecture
- Data synchronization
- Conflict resolution
Skills You Reference
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.
- 7d ago First seen · 509 lines · 47 tokens per session scan A ce2d87ed94be
flutter-backend-specialist is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 22d ago), licensed MIT. It adds 47 tokens to every session and 3,093 once invoked, about $0.0002 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 agents, from other repositories
backend_integration_agent
An agent for planning how an iPhone app connects to online services. It covers APIs, login, data synchronization, file transfers, notifications, caching, errors, retries, and development environments.
network-impl
Network layer implementation specialist. Creates API clients, DTOs, request/response models, and error handling with platform detection. Android: Ktor + kotlinx.serialization. iOS: URLSession + async/await + Codable. KMP: shared Ktor in commonMain.
api-integrator
API integration specialist. Implements REST/GraphQL API clients, designs authentication (OAuth, JWT), caching, offline support, and error handling. Optimizes the data flow between server and app.
api-designer
Designs the contract between mobile clients and servers. Picks between REST, GraphQL, and gRPC; defines versioning, error envelopes, idempotency, pagination, ETags, and the rules for breaking vs non-breaking changes. Engage at the start of any feature that crosses the network.
firebase-specialist
Owns Firebase/Google Cloud usage on mobile: Auth, Firestore, FCM, Remote Config, App Check, Crashlytics, Analytics, and Cloud Functions. Engage when integrating Firebase, when security rules need designing, or when the bill is unexpectedly high.
tauri-v2-expert
Tauri v2 expert for Rust backend commands, IPC patterns (invoke, events, channels), security model (capabilities, permissions, CSP), cross-platform desktop/mobile apps, and plugin development. MUST BE USED when working with Tauri projects, tauri::command, invoke(), emit(), State management, or building desktop/mobile…