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/ericrisco/rsc-harnessnpx agentmods add skills/ericrisco/rsc-harness/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/ericrisco/rsc-harness/flutter)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/flutter"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/flutter/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/ericrisco/rsc-harness/flutter"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/flutter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00091 | $0.04361 |
| Opus 5.5 | $0.00036 | $0.01744 |
| Sonnet 5.5 | $0.00018 | $0.00872 |
| Haiku 4.5 | $0.00009 | $0.00436 |
Grade A, and why
flutter scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return handler.resolve(await dio.fetch(error.requestOptions)); How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter & Dart app architecture
The opinionated default stack for a production Flutter app: feature-first + layered folders,
Riverpod 3 with codegen for shared/async state, a typed go_router, freezed immutable
models, a dio data layer, and explicit Result<T, Failure> error modeling — all on Material 3.
Escape hatches are first-class: Bloc/Cubit instead of Riverpod when the team already runs Bloc,
and raw http/get_it are allowed — but pick one of each per app, never mix two. Pinned versions
this skill targets: Flutter 3.44 / Dart 3.12, Riverpod 3.0, go_router 17.2.x
(+ go_router_builder 4.3.x), freezed 3.x / json_serializable, dio 5.x, mocktail 1.x.
Boundaries
⚠️ SDD new-feature gate — read this first. If this skill fired on a new, non-trivial feature or behaviour change and there is no approved spec + plan under
02-DOCS/wiki/sdd/, STOP — do not write feature code yet. Hand off to../specify/SKILL.mdfirst: it runs brainstorm → spec → plan → tasks before any code, then routes back here once the plan is approved. Build here directly only for a genuinely one-line / low-risk change. Method:../sdd/SKILL.md.
This skill owns the pubspec.yaml subproject and nothing else in the repo. Hand off when the UI is
Compose Multiplatform (compose-multiplatform), SwiftUI/native iOS (swift-ios) or React Native
(react-native); when the work is on a FastAPI/Go/Next.js sibling in the same monorepo (use that
skill). For a pure Dart server/CLI with no widget tree, general Dart applies but skip the
UI/nav/perf references. For a single-file throwaway sample, say architecture is overkill and do not
impose layering.
Around the edges: harness owns the workspace 01-TOOLS/02-DOCS layer and flavor secrets; fastapi,
go and nextjs build the backends this app talks to; secure-coding reviews token handling and
deep-link validation; deployment handles store/CI release; design owns the Material 3 token system.
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.
- 1mo ago First seen · 401 lines · 91 tokens per session scan A 56c9ac7c7d4b
flutter is a skill published in the GitHub repository ericrisco/rsc-harness (231 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 4,361 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
flutter-developer
Build beautiful, performant Flutter applications for iOS, Android, and web. Covers state management, navigation, animations, platform channels, and deployment.
mobilewright-cli
Automate iOS and Android apps on simulators, emulators and real devices, explore screens and write Mobilewright tests.
Debroid CLI Debugger
Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.
noqa-testing
Use this skill when the user wants to boot and interact with iOS or Android devices/simulators — inspect the screen, execute actions, generate or edit test cases, or run UI tests via the noqa platform.
mobiloop-mobile-qa
Test mobile apps with MobiLoop MCP, collect device evidence, and fix and retest confirmed failures within the user's scope. Use for Flutter, React Native, Android, or iOS QA on an emulator, simulator, or device, including relevant mobile security checks.
flutter
Build Flutter widget interfaces, organize state and async behavior, and prepare platform integrations and release builds.