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-automation-chaingit 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-automation-chain)<a href="https://agentmods.dev/skills/arenukvern/mcp_flutter/flutter-mcp-automation-chain"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/flutter-mcp-automation-chain/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-automation-chain"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/flutter-mcp-automation-chain.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 | $0.00176 | $0.02086 |
| Opus 5.5 | $0.00070 | $0.00834 |
| Sonnet 5.5 | $0.00035 | $0.00417 |
| Haiku 4.5 | $0.00018 | $0.00209 |
Grade C, and why
flutter-mcp-automation-chain scanned grade C with 2 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 13d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/Arenukvern/mcp_flutter/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/Arenukvern/mcp_flutter/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter MCP Automation Chain
The toolkit's surfaces are one chain, not competing products. The app
registers ext.mcp.toolkit.* service extensions (mcp_toolkit), and every
surface drives those same extensions through the universal AutomationDriver
contract (universal_automation_interface, ADR-0038): observe (semantic
snapshot with refs/bounds) → act (tap/type/navigate) → verify
(snapshot again, read values). Agents learn one grammar regardless of the
target — Flutter apps, browsers (CdpDriver), OS-native tiers.
intentcall hints (MCP _meta) declarative build + lifecycle
│ (oka: oka.yaml → targets)
▼ │
┌──────────────┐ transport over ext.mcp.toolkit.* ▼
│ MCP fmt_* │ ◄── the same extensions ──► flutter_mcp_harness
│ CLI (fmtk) │ (ToolkitDriver implements Scenario / AppTargets /
│ dynamic │ AutomationDriver) VmClient / LogTap
│ app tools │
└──────────────┘ ◄── universal_automation_* contracts ──► CdpDriver (web)
The one ownership law
At most one owning attach session per app. The owning session (a flutter run, or an external runner's dev command like oka dev) is the only
compile-capable reload channel — a second attach on a session someone else
owns is the ADR-0014 failure mode (the second attach can kill the first).
Everything else in the chain is an observer: it reads the same VM service
and drives extensions, but never takes ownership. When an external runner owns
the session, it writes .flutter_mcp/runner-session.json (spec v2, ADR-0014)
so the toolkit and harness can find the VM and delegate reload/restart to the
owner. Absence of the file is the liveness signal.
Pick the surface
| Need | Surface | Skill / doc |
|---|---|---|
| Chat-driven debugging ("tap X, what changed?") | MCP fmt_* tools |
flutter-mcp |
| Script/CI one-shot commands (snapshot, exec, batch) | CLI (flutter-mcp-toolkit / fmtk) |
CLI vs MCP |
| Repeatable scenario as checked-in Dart, CI exit codes | flutter_mcp_harness |
flutter-mcp-e2e-harness |
| Build + install + launch + process lifecycle (Android/iOS devices) | oka (separate repo) | this skill, oka section below |
| Browser tier (web demos, WebMCP dogfood) | CdpDriver over CDP |
flutter-mcp-toolkit-maintain-web |
| Intent → driver routing without hardcoding transport | IntentDriverRouter + hints |
this skill, intentcall section |
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.
- 13d ago Changed · +1 lines 7b8c2b67b9d8
- 15d ago First seen · 160 lines · 176 tokens per session scan C 66542683be34
flutter-mcp-automation-chain is a skill published in the GitHub repository Arenukvern/mcp_flutter (389 stars, last pushed 5d ago), licensed MIT. It adds 176 tokens to every session and 2,086 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
simpod
Drive a booted iOS Simulator from an agent with the simpod CLI — stream it to a browser, tap/swipe/type, send hardware buttons, rotate, read the accessibility tree, set appearance/location/status bar, open URLs, manage permissions, and tail logs. macOS only.
at_client_skills-sdk
Use this skill when a developer is building a Dart or Flutter app that depends on atclient or atclientflutter from pub.dev, stores or shares data via the Atsign Protocol, needs onboarding (CRAM new-atsign, atKeys file, keychain, APKAM) or APKAM enrollment, asks how to open, own, stop or switch an AtClient or read its…
flutter-pre-caching
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
bloc
Use when creating a Cubit or Bloc, modeling state with sealed classes or status enums, wiring BlocBuilder/BlocListener/BlocProvider, writing bloc tests, or choosing between Cubit and Bloc.
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.