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-app-debuggit 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-app-debug)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/flutter-app-debug"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/flutter-app-debug/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-app-debug"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/flutter-app-debug.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 | $0.00184 | $0.01395 |
| Opus 5.5 | $0.00074 | $0.00558 |
| Sonnet 5.5 | $0.00037 | $0.00279 |
| Haiku 4.5 | $0.00018 | $0.00139 |
Grade A, and why
flutter-app-debug 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter / アプリデバッグ・起動、アタッチ
起動構成とデバイスを確定し、flutter run --print-dtd で起動したうえで Dart MCP(DTD)から内部状態を検査・操作する。
黒箱の画面操作フローは Maestro MCP 側であり、本 SKILL と混同しない。
いつ使うか
- 実機 / シミュレータでアプリを起動して確認したいとき
- ランタイムエラー、Widget ツリー、ホットリロードでデバッグしたいとき
- 既に起動中のアプリへ DTD アタッチしたいとき
手順概要
launch.jsonから起動構成を読む- デバイスを1つに確定する
flutter run --print-dtdで起動する(または既存 DTD にアタッチ)- Dart MCP の
dtdで接続し、目的の検査・操作を行う
コマンド実行時は、プロジェクト規定のツールチェイン(あれば)に従う。
Flutter の起動構成の把握
.vscode/launch.jsonを読むtypeがdartかつrequestがlaunchの構成を起動構成とするflutterModeがあればそれを実行モード(debug/profile/release)とする- 無ければ
debug
cwd/program/args/deviceIdを引き継ぐargsの--flavorや--dart-define-from-file等は省略しない
起動対象の把握
flutter devices
- 文脈・プロンプトからデバイスを決める
- 1台だけならそれを使う
- launch 構成の
deviceIdがあれば優先
- 対象は常に 1つ
- 判別不能なら次を出して中断する
起動対象のデバイスを確定できませんでした。
対象デバイスを指定してください。
実行
アプリを起動する
- Dart MCP に起動ツールが無い/無効な場合はシェルの
flutter runを使う --print-dtdは必須(後続の MCP 接続用)cwdを作業ディレクトリにし、programとargsを引き継ぐprofile/releaseならそれぞれ--profile/--releaseを付ける
flutter run -d ${deviceId} --print-dtd ${modeFlags} ${program} ${args}
- ログの DTD URI(
ws://...)を控えるhttp://...の VM Service URI は DTD ではない。混同しない
起動中のアプリにアタッチする
DTD URI を取得する
次の順で確定する。
- 直前の
flutter run --print-dtd出力 - プロンプトやユーザー指示
- Dart MCP の
dtd(listDtdUris)- working dir がホームに見える DTD は IDE 起動アプリ候補として優先してよい
不明なら次を出して終了する。
DTD URIが認識できませんでした。
DTD URIを指定してください。
例: `ws://127.0.0.1:63514/...`
DTD に接続する
- Dart MCP の
dtdでconnect(必要なら先にツールスキーマを確認する) listConnectedAppsで接続済みを確認してよい- 複数アプリがある場合は操作対象の
appUriを明示する
アプリを制御・検証する
| ツール | 用途 |
|---|---|
get_runtime_errors |
ランタイムエラー確認 |
widget_inspector |
Widget ツリー・選択状態 |
flutter_driver_command |
タップ・入力・スクショ等 |
hot_reload / hot_restart |
変更反映 |
flutter_driver_commandの前にwidget_inspector(get_widget_tree)で実在 Widget を確認し、推測セレクタを作らない- Dart MCP: Flutter 内部の状態・エラー・Widget
- Maestro MCP: 端末上の黒箱 UI 操作(本 SKILL と用途を混ぜない)
What ships with it
1 file 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.
- 2mo ago First seen · 120 lines · 184 tokens per session scan A 9b355abce1e8
flutter-app-debug is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 1,395 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-app-debug compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flutter-app-debugeaglesakura/agent-skills | Skill | 2 | 1mo ago | MIT | A | 184 | Claude Code, Codex |
| ios-fixgarrytan/gstack | Skill | 141k | today | MIT | A | 15 | Claude Code |
| node-connectopenclaw/openclaw | Skill | 394k | today | MIT | A | 39 | Claude Code, Codex |
| google-mobile-ads-validategoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 84 | Claude Code, Codex |
| jetpack-compose-performanceandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 41 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | today | MIT | A | 176 | Claude Code |
| swiftui-performance-auditsteipete/agent-scripts | Skill | 7.5k | 8d ago | MIT | A | 24 | Claude Code, Codex |