Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ChunkyTofuStudios/flutter-skillsnpx agentmods add skills/chunkytofustudios/flutter-skills/preview-widgetWrote 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/chunkytofustudios/flutter-skills/preview-widget)<a href="https://agentmods.dev/skills/chunkytofustudios/flutter-skills/preview-widget"><img src="https://agentmods.dev/badge/skills/chunkytofustudios/flutter-skills/preview-widget.svg" alt="Measured on agentmods" 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 | $0.00210 | $0.02953 |
| Opus 5 | $0.00105 | $0.01477 |
| Sonnet 5 | $0.00042 | $0.00591 |
| Haiku 4.5 | $0.00021 | $0.00295 |
Grade A, and why
preview-widget 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 8d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preview a Flutter widget in isolation
Render a single widget in Flutter's Widget Previewer so you and the human can iterate on it — design tweaks, light/dark variants, tablet sizing — without booting the full app. The agent screenshots the live preview headlessly; the human optionally opens the same localhost URL in their own Chrome to follow along.
When to use this
All three must hold — if any is false, this skill is the wrong tool:
- The project is a Flutter project (
pubspec.yamlat the cwd,lib/exists). - Flutter ≥ 3.35 is on PATH (or via
fvm flutter). The previewer is experimental on stable but stable enough to design against; older Flutters don't have it. - The user wants to iterate on a single widget, not a full screen or end-to-end flow. Full-screen visual work is what
design-polish+android-emulatoris for.
Setup (caller's machine)
| Requirement | How to satisfy |
|---|---|
| Flutter ≥ 3.35 | Run bash scripts/check_preview_support.sh — fails loudly with an upgrade hint if too old. Override the Flutter binary with FLUTTER_BIN=… (default: flutter, falls back to fvm flutter). |
| Google Chrome / Chromium | Used headlessly by screenshot_preview.sh to capture previews. macOS picks up /Applications/Google Chrome.app automatically; on Linux any of google-chrome, chromium, chromium-browser on PATH works. Override with CHROME_BIN=/path/to/chrome. |
bash 3.2+ (macOS default), awk, grep, find |
Standard. No Python or Node needed. |
There's no per-machine auth, account, or token — everything runs on localhost.
Bundled scripts
scripts/check_preview_support.sh— verifies Flutter ≥ 3.35 and prints the resolved binary + version. Exit 0 = ready, exit 1 = version too old, exit 127 = no Flutter found.scripts/start_preview.sh— launchesflutter widget-preview startin the background, parses the URL out of its log, and writes a small JSON state file. Idempotent: re-runs return the existing URL.--stoptears the server down. Default state dir:./.preview-widget/(override withPREVIEW_WIDGET_STATE_DIR).scripts/screenshot_preview.sh— headless-Chrome screenshot of the running previewer. Flags:--out <path>,--size WxH(default1600x2400),--wait <ms>(virtual-time budget, default10000),--url <url>(override the state file). Prints the absolute output path on stdout.scripts/list_previews.sh— grepslib/for@Preview(...),@<Custom>Preview(...), andextends (Multi)?Previewdefinitions so you don't re-add what's already there.
What ships with it
17 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.
- assets/multi_preview.dart.template 1.2 KB
- assets/preview_wrapper.dart.template 1.8 KB
- references/limitations.md 4.5 KB
- references/preview_annotations.md 5.3 KB
- references/wrapper_patterns.md 6.3 KB
- scripts/check_preview_support.sh 3.5 KB runs code
- scripts/list_previews.sh 1.9 KB runs code
- scripts/screenshot_preview.sh 6.7 KB runs code
- scripts/start_preview.sh 8.3 KB runs code
- tests/check.bats 2.0 KB
- tests/help.bats 2.0 KB
- tests/helpers.bash 5.5 KB runs code
- tests/list_previews.bats 2.2 KB
- tests/screenshot.bats 3.5 KB
- tests/start.bats 3.4 KB
- tests/stubs/chrome 989 B
- tests/stubs/flutter 2.4 KB
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.
- 8d ago First seen · 184 lines · 210 tokens per session scan A 23b6c47ac3c0
preview-widget is a skill published in the GitHub repository ChunkyTofuStudios/flutter-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 210 tokens to every session and 2,953 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
animate-expo
Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and…
leanback-to-compose-tv-migration
Provides instructions and architectural patterns for migrating Android TV applications from legacy Leanback UI Toolkit, Android Views, or Support Fragments to Jetpack Compose for TV (androidx.tv). Use this skill for Leanback to Compose migrations, including browse screen, settings screen, authentication screen, login…
maui-data-binding
Guidance for .NET MAUI XAML and C# data bindings — compiled bindings, INotifyPropertyChanged / ObservableObject, value converters, binding modes, multi-binding, relative bindings, fallbacks, and MVVM best practices. USE FOR: setting up compiled bindings with x:DataType, implementing INotifyPropertyChanged or…
web-haptics
Add haptic feedback to web apps using the web-haptics library. Use when building mobile-facing UIs that need tactile feedback on buttons, toggles, forms, pickers, and other interactive elements.
migrate-xml-views-to-jetpack-compose
Provides a structured workflow for migrating an Android XML View to Jetpack Compose. This skill details the step-by-step process, from planning and dependency setup, to theming and layout migration, validation and XML cleanup. Use this skill when you need to migrate an XML View to Jetpack Compose in an Android…
axiom-swiftui
Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, performance, architecture, gestures, debugging, iOS 26 features.