marionette-flutter-setup

marionette-flutter-setup is a skill for Claude Code, Codex from leancodepl/marionette_mcp. It costs 202 tokens per session (2,590 once invoked), scanned A, original, Apache-2.0.

A setup guide for connecting a Flutter app to Marionette, so an AI agent can inspect and control the app during debug or profile builds.

In plain words
What is it for?
Use it to add Marionette to the app, initialize it safely in debug builds, configure widget text and semantics, collect logs, and set screenshot sizing.
Why use it?
Without this wiring, the agent cannot connect to the app or see its widgets. It also helps keep the app-side package and control bridge ready to work together.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add Marionette to the app, initialize it safely in debug builds, configure widget text and semantics, collect logs, and set screenshot sizing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leancodepl/marionette_mcp/marionette-flutter-setup
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.

Any agent
npx skills add leancodepl/marionette_mcp --skill marionette-flutter-setup
Clone the repo
git clone --depth 1 https://github.com/leancodepl/marionette_mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for marionette-flutter-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/leancodepl/marionette_mcp/marionette-flutter-setup/github.svg)](https://agentmods.dev/skills/leancodepl/marionette_mcp/marionette-flutter-setup)
Your own site
<a href="https://agentmods.dev/skills/leancodepl/marionette_mcp/marionette-flutter-setup"><img src="https://agentmods.dev/badge/skills/leancodepl/marionette_mcp/marionette-flutter-setup/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.

agentmods 80×15 button for marionette-flutter-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/leancodepl/marionette_mcp/marionette-flutter-setup"><img src="https://agentmods.dev/badge/skills/leancodepl/marionette_mcp/marionette-flutter-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00202 $0.02590
Opus 5.5 $0.00081 $0.01036
Sonnet 5.5 $0.00040 $0.00518
Haiku 4.5 $0.00020 $0.00259

Measured 9d ago against content hash 974a5b104098, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marionette-flutter-setup 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 9d 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.

packages/marionette_flutter/skills/marionette-flutter-setup/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

marionette_flutter: set up an app

Marionette has two halves: marionette_flutter, the package in the app, which registers a VM service extension per action (ext.flutter.marionette.*), and the bridge the agent calls, marionette_mcp (MCP tools) or marionette_cli (shell commands). This skill prepares the app for either bridge and keeps the versions aligned. Driving the app is the job of marionette-flutter-drive-app.

Add the binding

connect (or any CLI command) only works if the target app initialized MarionetteBinding. Check main.dart (or ask) before changing anything — if the binding is already there and the agent can see the app's widgets, the app is ready.

flutter pub add marionette_flutter
void main() {
  if (kDebugMode) {
    MarionetteBinding.ensureInitialized();
  } else {
    WidgetsFlutterBinding.ensureInitialized();
  }
  runApp(const MyApp());
}

This is all a standard Material-widgets app needs. It runs inside main(), so any time you add or change it, hot restart — a hot reload doesn't re-execute main(), so the change will look like it did nothing. Gate every piece of Marionette wiring behind kDebugMode (or !kReleaseMode — see Device-config sweeps, below) so none of it ships in a release build: both are compile-time constants the release branch survives cleanly.

Custom design system? Teach Marionette about it

Zero-config setup only recognizes stock Material widgets (ElevatedButton, TextField, Switch, …) and extracts text only from Text, RichText, EditableText, TextField, and TextFormField. If the app wraps its own buttons, fields, or text — true of most production apps — get_interactive_elements will look sparse and tap(text: ...) will fail to find things that are clearly on screen. That's not a Marionette bug; it just doesn't know your widgets yet:

MarionetteConfiguration(
  // Recognize your custom interactive widgets.
  isInteractiveElement: (element) => switch (element.widget) {
    MyButton() || MyTextField() => true,
    _ => false,
  },
  // Extract their visible text for text-based matching and discovery.
  extractText: (element) {
    final widget = element.widget;
    if (widget is MyText) return widget.data;
    return null;
  },
)

Read the full file on GitHub · 211 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. 9d ago First seen · 211 lines · 202 tokens per session scan A 974a5b104098

Subscribe to this mod's changes

marionette-flutter-setup is a skill published in the GitHub repository leancodepl/marionette_mcp (500 stars, last pushed 9d ago), licensed Apache-2.0. It adds 202 tokens to every session and 2,590 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-28.

Related

marionette-flutter-setup compared with skills from other repositories

marionette-flutter-setup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
marionette-flutter-setupleancodepl/marionette_mcpSkill5009d agoApache-2.0A202Claude Code, Codex
orca-emulator-androidstablyai/orcaSkill117ktodayMITA102Claude Code, Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
android-tombstone-symbolicationdotnet/skillsSkill5.8kyesterdayMITA176Claude Code
dogfoodcallstack/agent-deviceSkill5.3kyesterdayMITA55Claude Code
winapp-mauimicrosoft/winappCliSkill1.4ktodayMITA68Claude Code
app_remixrome-os/romeSkill889todayMITA50Claude Code, Codex