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.
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 agentmods add instructions/k9i-0/ccpocket/claude-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/instructions/k9i-0/ccpocket/claude-md)<a href="https://agentmods.dev/instructions/k9i-0/ccpocket/claude-md"><img src="https://agentmods.dev/badge/instructions/k9i-0/ccpocket/claude-md.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 | $0.04376 | $0.04376 |
| Opus 5 | $0.02188 | $0.02188 |
| Sonnet 5 | $0.00875 | $0.00875 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
ccpocket CLAUDE.md 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccpocket
Claude Code / Codex 対応モバイルクライアント
プロジェクト構成
ccpocket/
├── packages/bridge/ # Bridge Server (TypeScript, WebSocket)
│ └── src/
│ ├── index.ts # エントリーポイント
│ ├── websocket.ts # WebSocket接続管理・マルチセッション
│ ├── session.ts # セッション管理 (SessionManager)
│ ├── claude-process.ts # Claude CLIプロセス管理 (SDK経由)
│ ├── codex-process.ts # Codex CLIプロセス管理 (SDK経由)
│ └── parser.ts # stream-json パース・型定義
├── apps/mobile/ # Flutter Mobile App
│ └── lib/
│ ├── main.dart
│ ├── features/ # Feature-first ディレクトリ
│ │ ├── chat_session/ # 共通チャットセッション (state/widgets)
│ │ ├── claude_session/ # Claude Code セッション画面
│ │ ├── codex_session/ # Codex セッション画面
│ │ ├── session_list/ # セッション一覧 (ホーム)
│ │ ├── connection/ # 接続・マシン管理
│ │ ├── diff/ # Diff表示画面
│ │ ├── gallery/ # ギャラリー画面
│ │ ├── message_images/ # メッセージ画像ビューア
│ │ ├── prompt_history/ # プロンプト履歴
│ │ ├── settings/ # 設定画面
│ │ ├── setup_guide/ # 初回セットアップガイド
│ │ └── debug/ # デバッグ画面
│ ├── models/messages.dart # メッセージ型定義
│ ├── providers/ # グローバルprovider
│ ├── services/bridge_service.dart # WebSocketクライアント
│ ├── utils/diff_parser.dart # Unified diffパーサー
│ └── widgets/ # 共有Widget
└── package.json # npm workspaces root
コマンド
Bridge Server
npm run bridge # 開発サーバー起動 (tsx)
npm run bridge:build # TypeScriptビルド
Flutter App
cd apps/mobile && flutter run # アプリ起動
cd apps/mobile && flutter test # テスト実行
開発用一括再起動
npm run dev # Bridge再起動 + Flutterアプリ起動
npm run dev -- <device-id> # デバイス指定付き
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 · 341 lines · 4,376 tokens per session scan A 6f3ccae405a4
ccpocket CLAUDE.md is an instructions file published in the GitHub repository K9i-0/ccpocket (1,060 stars, last pushed today), licensed MIT. It adds 4,376 tokens to every session, about $0.0219 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 instructions, from other repositories
mobile CLAUDE.md
Claude Code instructions for lichess-org/mobile, covering claude.md, project overview, development setup, initial setup and install dependencies.
OpenNutriTracker copilot-instructions.md
Copilot instructions for simonoppowa/OpenNutriTracker, covering copilot instructions and commits (quick reminder).
OpenNutriTracker CLAUDE.md
Claude Code instructions for simonoppowa/OpenNutriTracker: Canonical agent instructions for this repository live in AGENTS.md.
exfig CLAUDE.md
Instructions for DesignPipe/exfig, covering toon format convention, context7 for external libraries, claude.md, quick reference and build & test.
zeno-mobile-runner AGENTS.md
Instructions for johnmikel/zeno-mobile-runner, covering notes for coding agents, public metadata policy — read before committing, the rule that catches agents out, scanned surfaces and enable the pre-push hook — once per clone.
DPIP AGENTS.md
AGENTS.md instructions for ExpTechTW/DPIP, covering working in this repository, where things are written down, toolchain, sdk patches and running.