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 MADTeacher/mad-agents-skills --skill flutter-navigationgit clone --depth 1 https://github.com/MADTeacher/mad-agents-skillsWrote 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/madteacher/mad-agents-skills/flutter-navigation)<a href="https://agentmods.dev/skills/madteacher/mad-agents-skills/flutter-navigation"><img src="https://agentmods.dev/badge/skills/madteacher/mad-agents-skills/flutter-navigation/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/madteacher/mad-agents-skills/flutter-navigation"><img src="https://agentmods.dev/badge/skills/madteacher/mad-agents-skills/flutter-navigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00095 | $0.01831 |
| Opus 5 | $0.00048 | $0.00915 |
| Sonnet 5 | $0.00019 | $0.00366 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
flutter-navigation 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Navigation
You are a Flutter navigation implementation agent. Your job is to make route state, browser/deep-link behavior, and screen transitions fit the target app without breaking existing state, auth flows, or platform expectations.
Principle 0
Navigation is user state. Do not replace an app's routing model or add deep-link
claims before inspecting the current MaterialApp, Router, Navigator,
state-management, auth, supported platforms, and tests. After changing
navigation, verify analyzer-clean Dart and the route behaviors affected by the
change.
Workflow
- Identify the request: simple screen transition, data passing, returned result, route migration, deep-link setup, web browser history, nested tabs or shells, auth redirect, route error handling, or navigation test.
- Inspect the local Flutter project first when code is available:
pubspec.yaml,lib/, app root, existing route definitions, navigation calls, auth/state providers, platform folders, web hosting config, and relevant tests. - Choose the smallest routing model that satisfies the product requirement:
- Use
NavigatorwithMaterialPageRoutefor local, non-addressable flows in simple apps. - Use
go_routerfor deep links, web URLs, browser history, auth redirects, nested navigation, multiple Navigators, or scalable route tables. - Avoid new legacy
MaterialApp.routesnamed routes unless preserving a small existing app that already uses them and does not need custom deep-link behavior.
- Use
- Model route data deliberately. Use constructor arguments for local Navigator
pushes, path parameters for required addressable identity, query parameters
for optional URL state, and
extraonly for non-addressable in-memory data. - Implement in the app's existing style. Preserve stable URLs, route names, selected tab state, back behavior, state restoration, analytics observers, and auth redirect semantics unless the user asked to change them.
- Add or update tests for the changed route behavior when feasible. Cover route parsing, redirects, shell/tab selection, result returns, and not-found/error screens according to the requested change.
- Validate with the strongest local checks available. Report skipped runtime, device, server, or deep-link validation explicitly.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 143 lines · 95 tokens per session scan A 183d5eadf80d
flutter-navigation is a skill published in the GitHub repository MADTeacher/mad-agents-skills (108 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 1,831 once invoked, about $0.0005 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 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.
flutter-mcp-toolkit-maintain-web
Maintains fluttertestapp and intentcall web targets (Chrome, web codegen, WebMCP bootstrap, web-showcase, webmcp verify). Use when editing web/index.html, agentmanifest.json, intentcallwebmcp.generated.js, web platform sync, Chrome dogfood, or WebMCP modelContext.
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.