commit-rules

A set of rules for writing Korean commit messages and checking code before and after a commit.

In plain words
What is it for?
Use it when creating or proposing commits, preparing a branch, running the required Bun commands and recording an uncommitted summary of the change.
Why use it?
It keeps commits focused and makes their purpose, validation status and follow-up notes consistent. It also defines required formatting and checks such as formatting and linting.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/ohah/react-native-mcp/commit-rules
Clone the repo
git clone --depth 1 https://github.com/ohah/react-native-mcp

Made for: Cursor.

Per session 462 This file is loaded in full into every session.
When invoked 462 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00462 $0.00462
Opus 5 $0.00231 $0.00231
Sonnet 5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured yesterday against content hash 728e04d4e798, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-rules 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 yesterday.

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.

.cursor/rules/commit-rules.mdc · 59 lines

What it actually says

커밋 규칙

커밋 생성·제안 시 적용. 상세는 AGENTS.MD 참고.

메시지 형식

<type>(<scope>): <subject>

<body>

<footer>
  • Type (필수): feat | fix | refactor | test | docs | chore | style
  • Scope (선택): server | react-native | docs | scripts | config
  • Subject (필수): 한국어, 명령형, 50자 이하, 마침표 없음
  • Body (선택): 한국어, 72자마다 줄바꿈, 무엇을·왜 변경했는지 설명
  • Footer (선택): Breaking changes, Issue 번호

원칙

  1. 커밋당 단일 목적
  2. 관련 없는 변경은 별도 커밋으로 분리
  3. 각 커밋은 독립적으로 의미 있어야 함
  4. 작고 논리적인 단위로 커밋

예시

feat(server): MCP 서버 및 도구 지원 추가

- MCP 프로토콜 기반 서버 구현
- 여러 도구(Tool) 등록 및 실행 지원
fix(react-native): WebSocket 재연결 처리 수정

- 연결 끊김 시 재연결 로직 수정
- 지수 백오프 적용

커밋 전 (필수)

  • 브랜치: 새 작업 시 브랜치를 먼저 생성한 뒤 해당 브랜치에서 커밋.
  • mise exec -- bun run format 실행
  • mise exec -- bun run lint 실행
  • 통과 후 스테이징·커밋

커밋 후 (필수)

요약 MD 파일 작성 (제목, 작업 내용). 이 파일은 커밋하지 않음 (.gitignore 또는 unstaged 유지).

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. yesterday First seen · 59 lines · 462 tokens per session scan A 728e04d4e798

Subscribe to this mod's changes

commit-rules is a cursor rule published in the GitHub repository ohah/react-native-mcp (7 stars, last pushed 5mo ago), licensed MIT. It adds 462 tokens to every session, about $0.0023 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 2026-08-31.