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 leancodepl/marionette_mcp --skill marionette-flutter-setupgit clone --depth 1 https://github.com/leancodepl/marionette_mcpWrote 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/leancodepl/marionette_mcp/marionette-flutter-setup)<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.
<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>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 | $0.00202 | $0.02590 |
| Opus 5.5 | $0.00081 | $0.01036 |
| Sonnet 5.5 | $0.00040 | $0.00518 |
| Haiku 4.5 | $0.00020 | $0.00259 |
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.
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;
},
)
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.
- 9d ago First seen · 211 lines · 202 tokens per session scan A 974a5b104098
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.
marionette-flutter-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marionette-flutter-setupleancodepl/marionette_mcp | Skill | 500 | 9d ago | Apache-2.0 | A | 202 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | today | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | today | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | today | MIT | A | 50 | Claude Code, Codex |