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 eaglesakura/agent-skills --skill flutter-layered-architecture-workspacegit clone --depth 1 https://github.com/eaglesakura/agent-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/eaglesakura/agent-skills/flutter-layered-architecture-workspace)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/flutter-layered-architecture-workspace"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/flutter-layered-architecture-workspace/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/eaglesakura/agent-skills/flutter-layered-architecture-workspace"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/flutter-layered-architecture-workspace.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 | $0.00181 | $0.01295 |
| Opus 5.5 | $0.00072 | $0.00518 |
| Sonnet 5.5 | $0.00036 | $0.00259 |
| Haiku 4.5 | $0.00018 | $0.00129 |
Grade A, and why
flutter-layered-architecture-workspace 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter / ワークスペース構造
dart / Flutter の workspace モノレポとして、どの package があり、依存がどう揃い、どこでアプリをビルドするかを把握する。
コマンド例は flutter 本体で示す(mise / fvm 等はリポジトリ規約に任せる)。
いつ使うか
- ルート
pubspec.yamlのworkspace:から package 一覧・配置を読むとき - 子 package が
any+resolution: workspaceな理由/ルート overrides の役割を説明するとき - 配布アプリのビルド入口(多くは
app/)を確認するとき
いつ使わないか
outdatedで版を上げる・検証する具体手順 →flutter-layered-architecture-library-update- 「この機能のコードはどこ?」の探索レポート →
flutter-layered-architecture-code-search - レイヤー責務・DI の設計判断 →
flutter-layered-architecture-design - Flutter SDK の最新版調査 →
flutter-maintenance-check-latest-version
作業手順
- リポジトリルートの
pubspec.yamlを開く workspace:ブロックでローカル package 一覧を把握する- 必要なら
environment(sdk / flutter)とdependency_overridesの役割を確認する - ビルド対象が
app(または同等のアプリ package)かを確認する - 依存の 更新作業に入るなら
library-updateへ引き継ぐ
原則(要約)
workspace でローカル package を列挙する
- アプリ固有 package はルート
pubspec.yamlのworkspace:に載る - ここからレイアウトを読み、レイヤー慣例(
screen_*/usecase_*等)と突き合わせて候補を絞る
workspace:
- app
- app_packages/data/database
# 以下、ローカル package が列挙される
アプリは app package でビルドする(慣習)
- ユーザー向けアプリの入口は多くの場合
app/
cd app/
flutter build ...
実効依存はルート dependency_overrides で揃える
- 子 package は
publish_to: "none"+resolution: workspace、依存は多くany - 版の固定・揃えはルート overrides(更新の手順詳細は library-update)
# ルート pubspec.yaml(例)
environment:
sdk: ">=3.12.0 <4.0.0"
flutter: ">=3.44.0 <4.0.0"
dependency_overrides:
some_package: "^1.0.0"
# 子 package の pubspec.yaml(例)
publish_to: "none"
resolution: workspace
environment:
sdk: ">=3.12.0 <4.0.0"
flutter: ">=3.44.0 <4.0.0"
dependencies:
flutter:
sdk: flutter
some_package: any
ディレクトリ名やプレフィックスはリポジトリにより違うが、ルート workspace + overrides / 子は any の形を優先して読み替える。
隣接 SKILL
| やりたいこと | 寄せ先 |
|---|---|
| overrides を実際に上げて検証 | flutter-layered-architecture-library-update |
| 機能・レイヤーのソース所在 | flutter-layered-architecture-code-search |
| レイヤー責務・依存方向 | flutter-layered-architecture-design |
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.
- 2mo ago First seen · 122 lines · 181 tokens per session scan A e764b5a9b39c
flutter-layered-architecture-workspace is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 181 tokens to every session and 1,295 once invoked, about $0.0007 per session on Opus 5.5. 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.
flutter-layered-architecture-workspace compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flutter-layered-architecture-workspaceeaglesakura/agent-skills | Skill | 2 | 1mo ago | MIT | A | 181 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 118k | today | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | today | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | today | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | today | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 894 | today | MIT | A | 50 | Claude Code, Codex |