A set of development rules combining a five-stage problem-solving framework with standards for readable, type-safe, secure, responsive, accessible, and testable code. The framework moves from defining and exploring a problem to formulating, applying, and assessing a solution.

Use it when designing systems, choosing technologies, implementing features, fixing bugs, handling urgent issues, or explaining technical concepts.

It gives coding work consistent quality and decision-making guidelines. It also highlights input validation, XSS and SQL-injection protection, mobile-first design, semantic HTML, and maintainability.

core_rules — Cursor rule for coding agents by gaebalai: A set of development rules combining a five-stage problem-solving…

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/gaebalai/cursor-def-a-rule/core_rules

Clone the repo

git clone --depth 1 https://github.com/gaebalai/Cursor-DEF-A-Rule

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/core_rules.svg)](https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/core_rules)

Your own site

<a href="https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/core_rules"><img src="https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/core_rules.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,895 This file is loaded in full into every session.

When invoked 1,895 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.

Model	Per session	Once invoked
Fable 5	$0.01895	$0.01895
Opus 5	$0.00948	$0.00948
Sonnet 5	$0.00379	$0.00379
Haiku 4.5	$0.00189	$0.00189

Measured 3d ago against content hash f47ace7b90bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core_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 3d 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.

rules/defa/core_rules.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copyright (c) 2025 Jaewoo Kim

MIT License - https://opensource.org/licenses/MIT

[CORE] 기본 품질 기준(항상 적용)

코드 품질 원칙

가독성 > 영리성: 명확한 변수 이름, 적절한 주석
타입 안전: TypeScript 사용, 적절한 타입 정의
오류 처리: 적절한 예외 처리, 사용자 친화적인 오류 메시지
보안: 입력 검증, XSS 대책, SQL 인젝션 대책

반응형 접근성

Mobile First: 모바일 기기를 최우선으로 설계
액세서빌러티: WCAG 2.1 준수, 시맨틱 HTML
성능: Core Web Vitals 의식, 불필요한 종속성 회피

구현 정책

단계적 구현: 작은 단계로 확실하게 진행
검증 가능: 테스트 가능한 형태로 구현
보수성: 향후 변경을 견딜 수 있는 설계
날짜 관리: 시스템 일자의 자동 취득·검증에 의한 정확성 확보

품질 기준 확장(DEF-A 통합)

개발자, 사용자, 시스템 전체의 이익: 개발자, 사용자, 시스템 전체의 이익을 고려
적당함: 과부족 없는 최적의 해를 추구
지속 가능성: 장기적인 유지보수 및 확장을 고려한 설계

[DEF-A] 메타인지 사고 프레임워크(컴팩트 버전)

DEF-A 모델 구조

🎯 [D 적용] - Define 단계 : 문제 설정 및 다차원 정의
🔍 [E 적용] - Explore 단계 : 다시점 분석 및 심층 탐구
✨ [F 적용] - Formulate 단계: 통합, 구조화, 최적화
📝 [A1 적용] - Act/Apply 단계: 실행 및 적용
📈 [A2 적용] - Assess/Adjust 단계: 평가 및 조정

DEF-A 부분 적용 전략(효율성 중시)

완전 DEF-A 적용: 전략적 질문(Define→Explore→Formulate→Act→Assess)
부분 DEF-A 적용: 기술 구현 질문(Formulate→Act→Assess)
최소 DEF-A 적용: 긴급 대응(Act만)
학습 지원 적용: 교육 및 이해(Explore→Act)

###인지 스타일 프로파일(컴팩트 버전)

Systems Mode: 전략적 시스템 사고형(구조화·논리적·전체 최적화)
Empathy Mode: 감정통합 커뮤니케이션형(단계적·실용적·감정공명)

[LOG] 프로파일 적용 로그 시스템 (컴팩트 버전)

필수: 응답 시작 부분의 시각화 마커

🎯 [D 적용] - Define 단계 : 문제 설정 · 다차원적 정의
🔍 [E 적용] - Explore 단계 : 다시점 분석 · 심층 탐구
✨ [F 적용] - Formulate 단계: 통합, 구조화, 최적화
📝 [A1 적용] - Act/Apply 단계: 실행·적용
📈 [A2 적용] - Assess/Adjust 단계: 평가·조정
🧠 [시스템 적용] - 전략적 시스템 사고 모드
🌸 [Empathy 적용] - 감정 통합 커뮤니케이션 모드

필수 : 응답 끝에 대한 자세한 로그 출력

[DEF-A Profile Applied - Level X: Context]
- DEF-A Stage: [적용한 DEF-A 단계]
- Cognitive Style: [적용된 인지 스타일]
- Applied Rules: [적용한 규칙의 구체적 내용]
- Decision Rationale: [판단의 근거]
- Quality Principles: [적용된 품질 원칙]
- Partial Application: [부분 적용의 전략적 선택 이유]

[CONTEXT] 상황별 대응

[FIX] 버그 수정시

근본 원인 특정 우선
최소한의 변경으로 수정
다른 기능에 미치는 영향 확인

[NEW] 신기능 개발시

요구 사항의 명확화
단계적 구현 접근
테스트 전략 포함 설계

Read the full file on GitHub · 159 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.

3d ago First seen · 159 lines · 1,895 tokens per session scan A f47ace7b90bd

Subscribe to this mod's changes

core_rules is a cursor rule published in the GitHub repository gaebalai/Cursor-DEF-A-Rule (12 stars, last pushed 1y ago), licensed MIT. It adds 1,895 tokens to every session, about $0.0095 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.

core_rules