ccpocket: Skill for Claude Code

.claude/skills/release-app/SKILL.md

release-app is a skill for Claude Code from K9i-0/ccpocket. It costs 87 tokens per session (2,144 once invoked), scanned A, original, MIT.

A release workflow for a Flutter app that updates its version, records changes, creates platform tags, and lets GitHub Actions build and distribute the app. Flutter is a toolkit for making apps for mobile, desktop, and other platforms.

In plain words
What is it for?
Use it when raising an app version or publishing a release for iOS, Android, macOS, Linux, or Windows. It helps review changes, choose the version and platforms, update the changelog, and start the automated release process.
Why use it?
It removes the repeated manual work of preparing releases across several platforms. It also keeps the version, changelog, tags, builds, and GitHub Release aligned.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

This is K9i-0/ccpocket's own configuration. It tells Claude Code how to work on ccpocket itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ccpocket configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(git:*), Bash(grep:*), Bash(gh:*), Bash(bash scripts/release/run-checks.sh), Bash(node scripts/release/monitor.mjs:*), Read, Edit, AskUserQuestion.

About the project

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.

K9i-0/ccpocket · 1,065 stars · on GitHub · k9i-0.github.io

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/K9i-0/ccpocket/main/.claude/skills/release-app/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/K9i-0/ccpocket

Made for: Claude Code.

Wrote 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.

agentmods badge for release-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/k9i-0/ccpocket/release-app.svg)](https://agentmods.dev/skills/k9i-0/ccpocket/release-app)
Your own site
<a href="https://agentmods.dev/skills/k9i-0/ccpocket/release-app"><img src="https://agentmods.dev/badge/skills/k9i-0/ccpocket/release-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.02144
Opus 5 $0.00044 $0.01072
Sonnet 5 $0.00017 $0.00429
Haiku 4.5 $0.00009 $0.00214

Measured 8d ago against content hash e8b980a02cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

release-app 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 8d 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.

.claude/skills/release-app/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

アプリ リリース

Flutter アプリのリリースを行う。 タグ push 後は GH Actions が自動でビルド・署名・配布・GitHub Release を作成する。

前提

  • main ブランチで作業中であること
  • 未コミットの変更がないこと

手順

1. 現在のバージョン確認 & 変更内容の収集

grep '^version:' apps/mobile/pubspec.yaml

version: X.Y.Z+N の形式。+N は build number。

前回リリースからの差分を確認する:

# 前回のタグ(iOS/Android/macOS/Linux/Windows のいずれか新しい方)
git tag -l 'ios/v*' 'android/v*' 'macos/v*' 'linux/v*' 'windows/v*' --sort=-v:refname | head -1

# 差分コミット(bridge 以外)
git log $(git tag -l 'ios/v*' 'android/v*' 'macos/v*' 'linux/v*' 'windows/v*' --sort=-v:refname | head -1)..HEAD --oneline -- apps/mobile/ CHANGELOG.md

2. バージョンとプラットフォームをユーザーに確認

差分コミットの内容を分析し、AskUserQuestion で 2つの質問を同時に 確認する。

質問 1: バージョン

選択肢の決定ルール:

  • feat コミットがある → minor を推奨(1番目の選択肢にし「(Recommended)」を付ける)
  • feat がなく fix のみ → patch を推奨
  • 破壊的変更がある → major を推奨

選択肢は具体的なバージョン番号で提示する(例: 「1.20.0+43 (minor)」「1.19.1+43 (patch)」)。 build number は現在の値 +1 で統一する。

質問 2: プラットフォーム

以下の選択肢を提示する:

  • iOS + Android + macOS + Linux + Windows 全部 (Recommended)
  • iOS + Android のみ(モバイルのみ)
  • macOS + Linux + Windows のみ(デスクトップのみ)
  • macOS のみ
  • Linux のみ
  • Windows のみ
  • iOS のみ
  • Android のみ

3. CHANGELOG 更新

CHANGELOG.md(ルート)の先頭に新しいセクションを追加する。

## [X.Y.Z] - YYYY-MM-DD

### Added
- ...

### Changed
- ...

### Fixed
- ...

ステップ 1 で確認したコミットを元に、Added / Changed / Fixed に分類する。 空のセクション(該当なし)は省略する。

4. バージョン bump

apps/mobile/pubspec.yamlversion をステップ 2 で決定したバージョンに更新する。

5. ローカル検証

タグpush前に、CDと同じチェックをcompactラッパーで実行する。 成功時は解析・テスト・合計時間の3行だけを返す。失敗時は一時ログのパスと 最大120行の末尾だけを返す。すべてpassしなければ次へ進まない。

bash scripts/release/run-checks.sh

失敗した場合はユーザーに報告し、修正を待つ。

6. コミット & push

git add apps/mobile/pubspec.yaml CHANGELOG.md
git commit -m "chore: bump version to X.Y.Z+N"
git push origin main

6.1. Windows preflight(Windowsを選択した場合)

Windowsタグを含むリリースでは、いずれのプラットフォームタグも作成する前に、 リリースコミットと同じSHAで起動した Test workflowの成功を確認する。 通常CIの mobile-windows jobが、リリースworkflowと同じFlutter全テストを windows-2022 で実行する。

Read the full file on GitHub · 189 lines

Changes

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.

  1. 8d ago First seen · 189 lines · 87 tokens per session scan A e8b980a02cef

Subscribe to this mod's changes

release-app is a skill published in the GitHub repository K9i-0/ccpocket (1,065 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 2,144 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

flutter

Use when building, structuring, testing or optimizing a Flutter app — feature-first layering, Riverpod 3 or Bloc, typed gorouter, freezed models, a dio data layer, Material 3, jank hunting, widget/golden tests. Targets Flutter 3.44 / Dart 3.12. NOT React Native (that is react-native), NOT Compose Multiplatform (that…

ericrisco/rsc-harness · 91 tokens

npm-publish

Publish the create-cmp CLI to npm as the create-cmp-cli package. Use this when the user asks to "publish create-cmp to npm", "release a new version", "ship create-cmp-cli", "npm publish this", "cut a release", or wants npx create-cmp-cli to work. Runs unattended when a granular npm token is installed in the user's…

kvdm-co-pilot/create-cmp · 150 tokens

release-new-version

Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).

niki914/zafiro · 54 tokens

testflight-release

Ship a new TestFlight build of the iOS companion (TermioMobile) — resolve the next build number against App Store Connect, archive, sign, export, upload, write the What to Test notes, and distribute. Invoke when the user says 'ship a testflight build', 'update testflight', 'upload to testflight', 'new beta build'…

termio-sh/termio · 102 tokens

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.

noqa-ai/noqa · 47 tokens

mobile-checkpoint

Checkpoint workflow for mobile development safety. Save/restore Android project state at critical points.

TalissonVitorino/kmp-ios-skills · 21 tokens