Team-MINO-Android: Command for Claude Code

.claude/commands/pr.md

pr is a command for Claude Code from mash-up-kr/Team-MINO-Android. It costs 18 tokens per session (3,994 once invoked), scanned A, original, Apache-2.0.

A command that creates a GitHub Pull Request, or PR, from the commits on the current branch into develop. It checks repository state and authentication, follows the project's PR template and branch rules, and can add a review comment from the author's perspective.

In plain words
What is it for?
Use it to prepare and submit a PR from the current branch, choose the correct base branch, push when needed, and highlight key changes for reviewers.
Why use it?
It standardises the final step of proposing completed work for review. The checks catch uncommitted changes, missing GitHub CLI login, and unclear target-branch choices before the PR is created.

Command for Claude Code

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

This is mash-up-kr/Team-MINO-Android's own configuration. It tells Claude Code how to work on Team-MINO-Android 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 Team-MINO-Android configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mash-up-kr/Team-MINO-Android. 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/mash-up-kr/Team-MINO-Android/develop/.claude/commands/pr.md
Clone the repo
git clone --depth 1 https://github.com/mash-up-kr/Team-MINO-Android

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 pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/mash-up-kr/team-mino-android/pr/github.svg)](https://agentmods.dev/commands/mash-up-kr/team-mino-android/pr)
Your own site
<a href="https://agentmods.dev/commands/mash-up-kr/team-mino-android/pr"><img src="https://agentmods.dev/badge/commands/mash-up-kr/team-mino-android/pr/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.

agentmods 80×15 button for pr

Your own site · 80×15
<a href="https://agentmods.dev/commands/mash-up-kr/team-mino-android/pr"><img src="https://agentmods.dev/badge/commands/mash-up-kr/team-mino-android/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,994 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.
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 $0.00018 $0.03994
Opus 5.5 $0.00007 $0.01598
Sonnet 5.5 $0.00004 $0.00799
Haiku 4.5 $0.00002 $0.00399

Measured today against content hash 6fec3e9480c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-03, from the pricing page.

Security

Grade A, and why

pr 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 today.

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/commands/pr.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pr — Pull Request 생성 커맨드

너는 현재 브랜치의 커밋과 연결된 이슈를 바탕으로 Pull Request 본문을 작성하고 gh pr create로 생성한 뒤, 작성자 관점의 Review Comment를 핵심 변경 지점에 남기는 Claude다. 푸시는 필요 시 자동으로 처리하되, 커밋 생성·수정은 범위 밖이다(/done 사용).

선행 로드: 이 커맨드는 아래 문서를 단일 출처로 한다. 반드시 Read해 최신 규칙을 확보한다.

  • docs/conventions/base-branch.md — 워크플로우 하위 작업의 base 자동판단 절차 (0-4 진입 전 Read)
  • docs/conventions/pull-request.md — 제목·섹션·연결 키워드·메타 규칙 (본문 작성 단계(5) 전 Read)
  • .github/PULL_REQUEST_TEMPLATE.md — 본문 스켈레톤 (본문 작성 단계(5) 전 Read)

0. 사전 검증

0-1. 워킹 트리 clean 확인

git status --porcelain

비어있지 않으면 중단:

❌ 커밋되지 않은 변경사항이 있습니다. 먼저 /done으로 커밋을 정리한 뒤 다시 실행해주세요.

0-2. gh 인증 확인

gh auth status

실패 시: "GitHub CLI 인증이 필요합니다. gh auth login 실행 후 다시 시도해주세요."

0-3. 보호 브랜치 경고 (차단 아님)

current=$(git symbolic-ref --short HEAD)

current가 main/develop이면 경고 출력 후 계속 진행:

⚠️ 현재 브랜치가 <main|develop> 입니다. 보호 브랜치에서 PR을 생성하는 것은 지양되지만 상황에 따라 필요할 수 있습니다. 그대로 진행합니다.

0-4. base 브랜치 결정

  • 현재 브랜치가 hotfix/* 또는 release/* 등 예외 패턴이면 AskUserQuestion으로 base 확인 (후보: develop, main)
  • 그 외에는 docs/conventions/base-branch.md의 "base 자동판단 절차"를 그대로 실행한다 — git 조상 관계로 현재 브랜치가 실제로 어느 브랜치에서 분기됐는지 확인해 조용히(질문 없이) base를 정한다. 절차·스크립트는 그 문서가 단일 출처.

0-5. 커밋 존재 확인 (base 대비)

git fetch origin <base>
git rev-list --count origin/<base>..HEAD

0이면 중단:

❌ <base> 대비 앞선 커밋이 없습니다. 커밋을 먼저 생성한 뒤 다시 실행해주세요.


1. 원격 동기화 (자동 푸시)

현재 브랜치의 upstream 및 원격 상태 확인:

git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null
git status -sb

upstream이 없거나 로컬이 원격보다 앞서있으면 자동 푸시:

git push -u origin "$current"

푸시 실패 시 실패 이유 출력 후 중단.


2. 중복 PR 체크

gh pr list --head "$current" --state open --json number,url,title

결과가 있으면 PR을 생성하지 않고 기존 PR URL을 출력한 뒤 종료:

ℹ️ 이미 열린 PR이 있습니다:


3. 연결 이슈 추출

브랜치 이름에서 이슈 번호를 파싱:

  • 패턴: <prefix>/<N>-<slug> → N 추출
  • 매칭 실패 시 AskUserQuestion으로 이슈 번호 직접 입력 요청 (또는 "이슈 없음" 선택 가능)

Read the full file on GitHub · 335 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. today First seen · 335 lines · 18 tokens per session scan A 6fec3e9480c6

Subscribe to this mod's changes

pr is a command published in the GitHub repository mash-up-kr/Team-MINO-Android (7 stars, last pushed 16d ago), licensed Apache-2.0. It adds 18 tokens to every session and 3,994 once invoked, about $0.0001 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 2026-10-02.