CC Pocket is a mobile and desktop client for controlling Codex and Claude coding-agent sessions through a self-hosted Bridge Server running on another computer. It lets users start sessions, approve actions, answer questions, review changes, and continue coding from supported devices. The catalogue entries provide the skills, hooks, MCP servers, agents, instructions, and settings used by this client.
Borrowing it
Nothing to install: this file belongs to K9i-0/ccpocket. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/K9i-0/ccpocket/main/.claude/skills/mobile-automation/SKILL.mdgit clone --depth 1 https://github.com/K9i-0/ccpocketWrote 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/k9i-0/ccpocket/mobile-automation)<a href="https://agentmods.dev/skills/k9i-0/ccpocket/mobile-automation"><img src="https://agentmods.dev/badge/skills/k9i-0/ccpocket/mobile-automation/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/k9i-0/ccpocket/mobile-automation"><img src="https://agentmods.dev/badge/skills/k9i-0/ccpocket/mobile-automation.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 | $0.00138 | $0.04307 |
| Opus 5 | $0.00069 | $0.02153 |
| Sonnet 5 | $0.00028 | $0.00861 |
| Haiku 4.5 | $0.00014 | $0.00431 |
Grade A, and why
mobile-automation 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 10d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Automation
dart-mcp と Marionette MCP を使ったFlutterアプリのUI検証・E2E自動化ガイド。
デフォルト設定
特別な指示がない限り、以下をデフォルトとして使う:
- デバイス: iOSシミュレーター（
flutter devicesで確認し、iPhone Simulator を選択） - Bridge ポート:
8766（テスト用。本番の8765と分離してテストできる） - プロジェクトルート: リポジトリルート（
git rev-parse --show-toplevelで取得） - アプリルート:
<プロジェクトルート>/apps/mobile
ユーザーが実機やポート8765を指定した場合はそちらに従う。
サブエージェント活用
E2E検証は e2e-verifier サブエージェント に委譲すると効率的。独立したコンテキストで検証するため、実装バイアスなく客観的に動作を確認できる。
Agent tool で e2e-verifier サブエージェントを起動:
subagent_type: e2e-verifier
プロンプト:
---
アプリが起動済みです。以下の検証を実施してください。
## 検証内容
[検証したい項目を記述]
## 接続情報
- VM Service URI: [wsUri]
- PID: [pid]
日本語で回答してください。
---
使い分け:
- 単純なUI確認（要素の存在チェック、1-2画面の確認）→ 直接MCP操作
- 包括的なE2E検証（複数画面のフロー、回帰テスト）→
e2e-verifierサブエージェントに委譲
アプリ起動ワークフロー
Step 1: デバイス確認
flutter devices
出力からシミュレーターのデバイスIDを確認する（例: 1A2B3C4D-5E6F-...）。
Step 2: アプリ起動
mcp__dart-mcp__launch_app
root: <アプリルートの絶対パス>
target: lib/main.dart
device: <シミュレーターのデバイスID>
返り値の pid を控える（以降の全ステップで必要）。
Step 3: 待機
5秒待機する。 Xcodeビルド + シミュレーターへのデプロイが完了するまで待つ必要がある。初回ビルド時は10秒程度かかることもある。
Step 4: VM Service URI 取得
mcp__dart-mcp__get_app_logs
pid: <Step 2のpid>
ログ出力から app.debugPort イベントを探し、wsUri を抽出する:
"params": { "wsUri": "ws://127.0.0.1:XXXXX/YYYY=/ws" }
wsUri が見つからない場合はビルドがまだ完了していない。5秒待って再度 get_app_logs を呼ぶ。
Step 5: Marionette 接続
mcp__marionette__connect
uri: <wsUri>
Marionette MCP は自動接続しないため、この手動 connect が必須。省略するとその後のUI操作が全て失敗する。
Step 6: 接続確認
mcp__marionette__get_interactive_elements
UI要素の一覧が返れば接続成功。
CLI vs MCP の使い分け
原則: DTD/VM Service接続が必要な操作はMCP、それ以外はCLI
MCP が必要な操作はアプリのランタイムに接続して情報を取得・操作するもの（起動、停止、ホットリロード、UI操作、ログ取得など）。一方、ビルドツールや静的解析のようにアプリのランタイムに依存しない操作はCLIの方が速くて確実。
MCP 操作一覧
| 操作 | ツール | MCP名 |
|---|---|---|
| アプリ起動 | Dart MCP | launch_app |
| アプリ停止 | Dart MCP | stop_app |
| アプリログ取得 | Dart MCP | get_app_logs |
| DTD接続 | Dart MCP | connect_dart_tooling_daemon |
| ホットリロード | Dart MCP | hot_reload |
| ホットリスタート | Dart MCP | hot_restart |
| ウィジェットツリー | Dart MCP | get_widget_tree |
| ランタイムエラー | Dart MCP | get_runtime_errors |
| VM Service接続 | Marionette | connect |
| UI要素一覧 | Marionette | get_interactive_elements |
| タップ | Marionette | tap |
| ダブルタップ | Marionette | double_tap |
| 長押し | Marionette | long_press |
| テキスト入力 | Marionette | enter_text |
| スワイプ/ドラッグ | Marionette | swipe |
| ピンチズーム | Marionette | pinch_zoom |
| 戻る操作 | Marionette | press_back_button |
| スクロール | Marionette | scroll_to |
| アプリログ | Marionette | get_logs |
| スクリーンショット | Marionette | take_screenshots |
| カスタム拡張一覧 | Marionette | list_custom_extensions |
| カスタム拡張呼び出し | Marionette | call_custom_extension |
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.
- 10d ago First seen · 334 lines · 138 tokens per session scan A 10ec0283a16a
mobile-automation is a skill published in the GitHub repository K9i-0/ccpocket (1,065 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 4,307 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
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.
zmr-mobile-testing
Use when testing mobile apps with Zeno Mobile Runner, integrating app-local .zmr setup, driving Android or iOS simulator scenarios, using JSON-RPC or MCP agent sessions, exporting traces, or comparing mobile runner benchmarks.
android-e2e-readiness
Use when Android mobile E2E flows are flaky, Compose and View screens disagree with automation, hybrid screens are ambiguous, retries hide the real issue, or the team keeps collapsing the problem to selector-vs-timing without checking Android-specific readiness contracts.
ios-e2e-readiness
Use when iOS mobile E2E flows are flaky, SwiftUI and UIKit surfaces disagree with automation, mixed screens are ambiguous, retries hide the real issue, or the team keeps collapsing the problem to timing-only or SwiftUI-only without checking iOS-specific readiness contracts.
mobile-e2e-readiness-baseline
Use when mobile E2E flows are flaky across Android and iOS, visible screens are not reliably actionable, retries hide the real problem, or a team needs a platform-neutral readiness review before platform-specific guidance.
cmp-qa-prep
Bring up the E2E harness for a Kotlin/Compose Multiplatform app — boot the Android emulator, install the debug build, run the Maestro smoke — or, simpler, run the verify lane, which does all three itself. Use this when the user wants to run E2E/device tests on their CMP/KMP app, "prep my KMP test environment", "smoke…