electron-mcp-server: Cursor rule for Cursor

.cursor/agents/sub-agent-review.mdc

sub-agent-review is a cursor rule for Cursor from ohah/electron-mcp-server. It costs 36 tokens per session (1,044 once invoked), scanned A, original, MIT.

A set of rules for reviewing pull requests, which are proposed code changes shared for review. It covers scope, code quality, errors, security, performance, edge cases, and tests.

In plain words
What is it for?
Checking whether a pull request matches its purpose, identifying bugs and maintenance issues, and writing review summaries and inline suggestions.
Why use it?
It gives reviews a consistent checklist so important problems and differences between the stated goal and actual changes are less likely to be missed.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: model in frontmatter; mentions subagents.

This is ohah/electron-mcp-server's own configuration. It tells Cursor how to work on electron-mcp-server 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 electron-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ohah/electron-mcp-server. 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/ohah/electron-mcp-server/main/.cursor/agents/sub-agent-review.mdc
Clone the repo
git clone --depth 1 https://github.com/ohah/electron-mcp-server

Made for: Cursor.

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 sub-agent-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/ohah/electron-mcp-server/sub-agent-review/github.svg)](https://agentmods.dev/rules/ohah/electron-mcp-server/sub-agent-review)
Your own site
<a href="https://agentmods.dev/rules/ohah/electron-mcp-server/sub-agent-review"><img src="https://agentmods.dev/badge/rules/ohah/electron-mcp-server/sub-agent-review/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 sub-agent-review

Your own site · 80×15
<a href="https://agentmods.dev/rules/ohah/electron-mcp-server/sub-agent-review"><img src="https://agentmods.dev/badge/rules/ohah/electron-mcp-server/sub-agent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 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 $0.00036 $0.01044
Opus 5.5 $0.00014 $0.00418
Sonnet 5.5 $0.00007 $0.00209
Haiku 4.5 $0.00004 $0.00104

Measured 2mo ago against content hash 0cd6e44738a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sub-agent-review 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 2mo 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.

.cursor/agents/sub-agent-review.mdc · 58 lines

What it actually says

PR 리뷰 시점 (Review Perspective)

이 룰은 PR을 검토하고 리뷰(요약 + 인라인 제안)를 작성할 때 적용한다.

0. 브랜치·권한 (이 레포 ohah 전용)

  • 대상 브랜치: 리뷰는 현재 브랜치의 PR에 대해 수행한다. gh pr view / gh pr diff 는 현재 브랜치 기준이다.
  • gh 계정: 이 레포(ohah/electron-mcp-server)에서 리뷰를 제출할 때는 ohah GitHub 계정을 쓴다.
    • 리뷰 제출 전: gh api user -q .login 으로 현재 사용자 확인. ohah 가 아니면 gh auth switch --hostname github.com --user ohah 로 전환하고, 이전 로그인을 기억해 둔다.
    • 리뷰 제출 후: ohah 로 전환했었다면 gh auth switch --hostname github.com --user <이전_계정> 으로 복원하여 전역 gh 설정이 바뀌지 않게 한다.
  • 자세한 절차는 .cursor/commands/review.md 의 "gh account for this repo", "Order of operations" 1번을 참고한다.

1. 목적·설명 일치

  • Purpose / Work content: PR 본문의 목적·설명이 실제 변경(코드·파일)과 맞는지 확인한다.
  • Scope: 제목·본문에 나온 범위 밖의 변경이 포함되어 있지 않은지, 또는 포함된 변경이 본문에 누락되지 않았는지 확인한다.

2. 잘된 점 (What's done well)

  • 구조·네이밍: 디렉터리·파일·함수·변수 네이밍이 프로젝트 컨벤션과 일관된지.
  • 일관성: 기존 코드 스타일(포맷, 주석, 타입)과 맞는지.
  • 가독성: 로직이 읽기 쉽고 의도가 드러나는지.

3. 개선 제안 (Improvement suggestions)

  • 버그·엣지케이스: null/undefined, 빈 배열·문자열, 연결 해제 후 호출 등 경계 조건이 처리되었는지.
  • 예외·에러: try-catch, Promise reject, 콜백 예외가 적절히 처리·로깅·전파되는지.
  • 성능: 불필요한 반복, 메모리 누수(타이머·리스너 해제), 대량 데이터 처리 등.
  • 보안: 외부 입력 파싱·검증, 민감 정보 노출 여부(로그·에러 메시지).
  • 테스트: 변경된 경로에 대한 테스트·커버리지가 있는지, 회귀 방지가 고려되었는지.

4. 인라인 제안 (Line-level suggestions)

  • 구체적 수정: 코드 한 줄·몇 줄만 바꾸면 개선되는 경우, 해당 파일·라인에 인라인 코멘트로 제안한다.
  • 형식: 설명 문장 + (적용 가능한 경우) ```suggestion ``` 블록으로 제안 코드를 넣어, GitHub "Commit suggestion"으로 적용 가능하게 한다.
  • 라인 번호: 인라인은 diff의 새 버전(우측) 기준 라인 번호를 사용하며, 실제 파일과 맞는지 확인한다.

5. 테스트 관점

  • How to test: 리뷰어가 로컬에서 어떻게 확인할 수 있는지 본문에 있는지, 없으면 요약해서 리뷰에 적는다.
  • 회귀: 기존 동작을 깨뜨리지 않는지, 필요한 경우 회귀 테스트 방법을 제안한다.

체크리스트 (리뷰)

  • (이 레포) 현재 브랜치의 PR인지 확인했는가? 리뷰 제출 전 ohah로 전환·제출 후 복원했는가?
  • PR 목적·설명과 변경 내용이 일치하는가?
  • 잘된 점(구조·네이밍·일관성)을 요약했는가?
  • 개선 제안(버그·엣지케이스·성능·테스트)을 구체적으로 적었는가?
  • 인라인 제안이 있으면 파일·라인·suggestion 블록을 정확히 넣었는가?
  • 테스트·확인 방법을 리뷰에 포함했는가?
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. 2mo ago First seen · 58 lines · 36 tokens per session scan A 0cd6e44738a2

Subscribe to this mod's changes

sub-agent-review is a cursor rule published in the GitHub repository ohah/electron-mcp-server (4 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 1,044 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 2026-08-31.