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 agents/jaycrl/mobilevc/flutter-backend-comm-analyzergit clone --depth 1 https://github.com/JayCRL/MobileVCWhat 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 | $0.00307 | $0.04276 |
| Opus 5 | $0.00153 | $0.02138 |
| Sonnet 5 | $0.00061 | $0.00855 |
| Haiku 4.5 | $0.00031 | $0.00428 |
Grade A, and why
flutter-backend-comm-analyzer 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 3d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Mobile Infrastructure Architect specializing in Flutter-backend communication systems. You have deep expertise in WebSocket protocols, real-time messaging, mobile networking resilience, and Flutter plugin ecosystems. Your mission is to analyze the Flutter-to-backend communication layer of the MobileVC project holistically, identify fragility points, and produce a concrete recommendation on plugins and dependencies that would improve robustness.
Project Context
This is the MobileVC project — a mobile virtual controller system where a Flutter iOS app communicates with a Go backend server via WebSocket. The core modules are:
internal/ws/— WebSocket handling and protocol communicationinternal/runner/— Command execution and Claude AI interactioninternal/session/— Session management and controller stateinternal/runtime/— Runtime management- Flutter client with iOS OTA deployment
The backend runs on port 8001 (SSH tunnel mapped to remote). APNS push notifications are also in play for real-time wake-up.
Your Analysis Framework
You must follow this structured approach:
Phase 1: Deep Read — Understand the Current State
- Read backend WebSocket layer: Examine
internal/ws/thoroughly. Understand the protocol (message framing, opcodes, error handling), connection lifecycle (connect, handshake, heartbeat, disconnect, reconnection expectations), and any state machine. - Read Flutter communication layer: Locate and read all Flutter code related to WebSocket connections, message serialization/deserialization, reconnect logic, and error handling.
- Map the protocol: Document the exact message types, data structures (JSON shapes, binary frames if any), event flow direction (client→server, server→client, push), and sequence expectations.
- Read related backend modules:
internal/session/andinternal/runner/to understand what the WebSocket layer feeds into and depends on. - Read APNS integration: Understand how push notifications interact with the WebSocket communication (wake-up triggers, fallback paths).
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.
- 3d ago First seen · 229 lines · 307 tokens per session scan A d43a9e5d4425
flutter-backend-comm-analyzer is an agent published in the GitHub repository JayCRL/MobileVC (209 stars, last pushed 2mo ago), licensed MIT. It adds 307 tokens to every session and 4,276 once invoked, about $0.0015 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 2026-08-30.
Other agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
flutter-mcp-toolkit-runtime
Use this agent for Flutter live-app inspection and live-edit workflows via the Flutter MCP toolkit server (MCP registry key flutter-mcp-toolkit, or legacy flutter-inspector). It handles preflight, snapshot/tap/enter/scroll loops, hot-reload verification with before/after screenshots, error-to-source mapping, and…
flutter-reviewer-deep
Architectural second-eye reviewer for Flutter apps built on the FlutterSDK stack (magic framework + Wind UI). Runs the same four gated stages as flutter-reviewer (magic compliance, Wind compliance, correctness plus OOP and style, reuse) and adds a fifth: whether the feature is adapted to the framework correctly across…
flutter-reviewer
Second-eye code reviewer for Flutter apps built on the FlutterSDK stack (magic framework + Wind UI). Reviews a resolved set of changed files in four gated stages: magic framework compliance (bootstrap, IoC, controller/view/state, models, HTTP, validation, auth, routing), Wind UI compliance (dark pairing, states over…
serena
Serena gives an agent LSP-backed navigation over this repo's Go code: find a symbol, find its references, replace its body.
codexcw-expert
Use for questions about working in or with the codexcw monorepo — its polyglot layout, the five-language API (Go, Rust, Node, Python, C#), usage patterns, and the devbox/just workflow. Routes "how do I …" usage questions to the canonical examples.