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 skills add Arenukvern/mcp_flutter --skill flutter-mcp-toolkit-maintain-webgit clone --depth 1 https://github.com/Arenukvern/mcp_flutterWrote 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/skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-maintain-web)<a href="https://agentmods.dev/skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-maintain-web"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-maintain-web/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/skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-maintain-web"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-maintain-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00815 |
| Opus 5 | $0.00037 | $0.00407 |
| Sonnet 5 | $0.00015 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
flutter-mcp-toolkit-maintain-web 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 6d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Web (Chrome + WebMCP)
Dogfood app: flutter_test_app. Canonical platform doc: flutter_test_app/INTENTCALL_PLATFORM.md.
WebMCP vs VM MCP
| Path | Proves |
|---|---|
VM extensions + fmt_* tools |
MCP toolkit dogfood (always) |
document.modelContext |
True WebMCP (Chrome flag / --web-browser-flag) |
ADR: decisions/0008_web_agent_invoke_js_only.mdx — JS fetch('/agent/invoke') 404 by design; Dart invokeDirect works when modelContext exists.
Launch (repeatable WebMCP)
make web-showcase
# WS_URI from .showcase/web_app.log (re-grep after hot reload)
grep -Eo 'ws://127\.0\.0\.1:[0-9]+/[A-Za-z0-9_=-]+/ws' .showcase/web_app.log | tail -1
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart webmcp chrome-args
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart webmcp verify --web-port 8080
Stop: make showcase-stop.
Do not rely on chrome://flags alone across machines — use webmcp chrome-args / make web-showcase.
Codegen & hooks
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart codegen sync \
--platform web,android,ios,macos,linux,windows \
--project-dir flutter_test_app
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart init intentcall-platform \
--project-dir flutter_test_app --check
| Artifact | Source |
|---|---|
web/intentcall_webmcp.generated.js |
codegen sync from web/agent_manifest.json |
web/index.html |
init intentcall-platform script tag |
| Dart bootstrap | registerAgentWebMcpFromEntries in mcp_toolkit_extensions.dart (debug web, after addEntries; intentcall_platform) |
Runtime validate
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart --save-images \
--output-dir .showcase/web_iter validate-runtime \
--target "$WS_URI" \
--flutter-device chrome \
--timeout-ms 45000
Pass --web-browser-debugging-port <cdp> if CDP discovery fails.
Known issues
- Duplicate tool name — generated JS +
registerAgentWebMcpFromEntriesboth callregisterTool; dedupe or gate one path (agent_web_mcp_bootstrap_web.dartname cache). - CDP probe —
webmcp verifymay reportwebmcp_active_log_evidencewhile CDPhasModelContextis false (Flutter execution context). - Stale WS_URI — always grep fresh token after hot restart before eval/validate.
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.
- 6d ago First seen · 78 lines · 74 tokens per session scan A 6f4f30bd39c5
flutter-mcp-toolkit-maintain-web is a skill published in the GitHub repository Arenukvern/mcp_flutter (373 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 815 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
flutter-use-column-row-first
Use when building any Flutter screen or component to choose responsive Row, Column, Expanded, Flexible, and Spacer layouts before fixed-size or coordinate-based alternatives.
signals-flutter
Highly optimized Flutter UI bindings and GPU rendering for reactive signals.
generating-flutter-ui
Generative UI (GenUI) for Flutter using AI models like Google Gemini, Anthropic Claude, or OpenAI via the genui package. Use this skill when building dynamic AI-driven interfaces, conversational UI flows, server-rendered screen layouts, LLM-powered dashboards, chat-based UI generation, or implementing prompt-to-UI…
flutter
Operational skill for Flutter: widgets, state management choices, async UI, platform channels awareness, and release build hygiene.
flutter-routing
Declarative routing and navigation for Flutter using GoRouter and AutoRoute. Use when implementing navigation guards, nested routes, type-safe routing, or deep link handling.
flutter-state-management
State management architecture for Flutter using Riverpod, Provider, and BLoC patterns. Use when choosing a state solution, implementing reactive state, resolving rebuild issues, or structuring MVVM/BLoC architecture.