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/fluttersdk/ainpx agentmods add skills/fluttersdk/ai/fluttersdk-duskWrote 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/fluttersdk/ai/fluttersdk-dusk)<a href="https://agentmods.dev/skills/fluttersdk/ai/fluttersdk-dusk"><img src="https://agentmods.dev/badge/skills/fluttersdk/ai/fluttersdk-dusk.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 | $0.00282 | $0.04868 |
| Opus 5 | $0.00141 | $0.02434 |
| Sonnet 5 | $0.00056 | $0.00974 |
| Haiku 4.5 | $0.00028 | $0.00487 |
Grade A, and why
fluttersdk-dusk 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 6d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fluttersdk_dusk
End-to-end driver for Flutter apps, designed for LLM agents. The running app
exposes a ext.dusk.* VM Service surface plus an MCP server; the agent calls
dusk_* tools (or ./bin/fsa dusk:* from a shell) to snap the Semantics
tree, mint ref tokens, gesture against them, wait for conditions, screenshot,
and hot-reload, all without a test file or rebuild between actions.
This skill assumes the app already has dusk installed (a kDebugMode-gated
DuskPlugin.install() in lib/main.dart, the MCP server in .mcp.json).
If not, run dart run fluttersdk_dusk dusk:install once from the app root
and verify with ./bin/fsa dusk:doctor.
1. Core Laws
-
Two ref token spaces.
e<N>(snapshot-frozen, minted bydusk_snap) are deduped bySemanticsNode.id: the same widget across consecutive snaps returns the samee<N>and the ref stays valid as long as the node remains mounted. They become defunct when the node unmounts (navigation, conditional render, list rebuild).q<N>(re-resolvable, minted bydusk_find/dusk_observe) store a predicate and re-walk the live tree on every action. Usee<N>right after the snap that minted them when the UI is static. Reach forq<N>whenever the action might retry, the UI animates, or the agent holds the ref across a navigation. Never mix the spaces (noe<N>from find, noq<N>from snap). -
The 6-step actionability gate is mandatory. Every
tap,hover,drag,dblclick,right_click,triple_click, andtypeis gate-checked in this order: (0) defunct, (1) enabled, (2) zero-rect, (3) off-viewport (auto-scrolls when aScrollableancestor exists, then re-checks), (4) stable (2-frame rect drift, 0.5px threshold), (5) receives-events (hit-test path includes the target). Steps 4 and 5 acceptcheckStable: false/checkReceivesEvents: falseoverrides for flaky animations or known overlays.scroll,select_option, andpress_keyskip the gate by design.
What ships with it
5 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.
- 6d ago First seen · 261 lines · 282 tokens per session scan A ea212c90210e
fluttersdk-dusk is a skill published in the GitHub repository fluttersdk/ai (2 stars, last pushed 3d ago), licensed MIT. It adds 282 tokens to every session and 4,868 once invoked, about $0.0014 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
flutter-testing
Write, fix, review, debug, and validate Flutter tests for apps, packages, and plugins. Use when adding unit tests, widget tests, integration tests, MethodChannel or plugin mocks, Mockito or mocktail test doubles, golden or accessibility checks, CI test commands, test failures, MissingPluginException, pump or…
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
flutter-mcp-cli-runtime-validation
Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.
quality-engineering-appium-mcp
Drives iOS/Android mobile devices via Appium MCP. Use for verifying mobile bugs, E2E tests, and navigating real device clouds (LambdaTest/BrowserStack).
t-flutter-demo-run-all
Run all Android Patrol user-story demo files with resumable checkpoints.
e2e-testing-mobile
Plans, generates, runs, and heals end-to-end tests for Expo and React Native mobile apps using Maestro (the 2026 standard for RN E2E, adopted by Meta, Microsoft, and DoorDash, and integrated with Expo via EAS Workflows). Drives a spec-first YAML-flow loop, proposes testID source diffs (never accessibilityLabel reuse)…