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.
git clone --depth 1 https://github.com/gaebalai/Cursor-DEF-A-RuleWrote 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.
[](https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/prompt_templates)<a href="https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/prompt_templates"><img src="https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/prompt_templates/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.
<a href="https://agentmods.dev/rules/gaebalai/cursor-def-a-rule/prompt_templates"><img src="https://agentmods.dev/badge/rules/gaebalai/cursor-def-a-rule/prompt_templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.01590 | $0.01590 |
| Opus 5 | $0.00795 | $0.00795 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
prompt_templates 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 148 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
[PROMPT] DEF-A 통합 프롬프트 템플릿 (최적화 버전)
기본 프롬프트 구조
# Cursor 프롬프트 - DEF-A 통합 지시
## [CONTEXT] 개발 상황
- **프로젝트**: [프로젝트명・특성]
- **개발 단계**: [요구사항 정의/설계/구현/테스트/운영]
- **긴급도**: [긴급/일반/학습]
- **팀 규모**: [개인/소규모/대규모]
- **프로젝트 특성**: [신규/기존/개인/팀]
## [REQUEST] 구체적인 요청
[구체적인 질문 및 요청 내용]
## [DEF-A] 사고 흐름 지정
- **적용 단계**: [Define/Explore/Formulate/Act/Assess 또는 복수 선택]
- **적용 전략**: [완전 적용/부분 적용/최소 적용/학습 지원 적용]
- **인지 스타일**: [Systems 사고 중시/Empathy 공감 중시/상황 판단]
- **복잡성 수준**: [간결/표준/상세]
## [RULES] 적용 규칙
- **주요 규칙**: [frontend/backend/testing/core]
- **보조 규칙**: [해당되는 경우]
- **품질 기준**: [공동의 이익/적절함/지속 가능성]
- **출력 형식**: [코드/설계서/설명/튜토리얼]
- **부분 적용 사유**: [효율성/긴급도/학습 지원/전략적 중요성]
적용 전략별 템플릿
완전 DEF-A 적용 (전략적 질문)
## [DEF-A] 사고 흐름 지정
- **적용 단계**: Define → Explore → Formulate → Act → Assess (완전 적용)
- **적용 전략**: 완전 적용 (전략적 중요성)
- **인지 스타일**: Systems 사고 중시 (시스템 전체 최적화)
- **복잡성 수준**: 상세
부분 DEF-A 적용 (기술 구현 질문)
## [DEF-A] 사고 흐름 지정
- **적용 단계**: Formulate → Act → Assess (구현 중시)
- **적용 전략**: 부분 적용 (구현 중시)
- **인지 스타일**: Systems 사고 중시 (구조화・타입 안정성)
- **복잡성 수준**: 표준
최소 DEF-A 적용 (긴급 대응)
## [DEF-A] 사고 흐름 지정
- **적용 단계**: Act (긴급 대응 구현만)
- **적용 전략**: 최소 적용 (긴급 대응)
- **인지 스타일**: Systems 사고 중시 (효율적・논리적 해결)
- **복잡성 수준**: 간결
학습 지원 적용 (교육 및 이해)
## [DEF-A] 사고 흐름 지정
- **적용 단계**: Explore → Act (학습・실습)
- **적용 전략**: 학습 지원 적용 (교육・이해)
- **인지 스타일**: Empathy 공감 중시 (단계적 설명・학습 지원)
- **복잡성 수준**: 상세
기술 영역별 규칙 선택
프론트엔드 개발
## [RULES] 적용 규칙
- **주요 규칙**: frontend_rules.mdc
- **보조 규칙**: core_rules.mdc
- **품질 기준**: 공동의 이익 (개발자・사용자・시스템 전체)
- **출력 형식**: [코드/설계서/설명/튜토리얼]
백엔드 개발
## [RULES] 적용 규칙
- **주요 규칙**: backend_rules.mdc
- **보조 규칙**: core_rules.mdc
- **품질 기준**: 공동의 이익 + 보안 중시
- **출력 형식**: [코드/설계서/설명/튜토리얼]
테스트 및 품질 보증
## [RULES] 적용 규칙
- **주요 규칙**: testing_rules.mdc
- **보조 규칙**: core_rules.mdc
- **품질 기준**: 지속 가능성 (팀의 장기적 성장)
- **출력 형식**: [코드/설계서/설명/튜토리얼]
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.
- 9d ago First seen · 148 lines · 1,590 tokens per session scan A 8be4a2ca31e0
prompt_templates is a cursor rule published in the GitHub repository gaebalai/Cursor-DEF-A-Rule (12 stars, last pushed 1y ago), licensed MIT. It adds 1,590 tokens to every session, about $0.0080 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.
Other cursor rules, from other repositories
baml
A set of rules for setting up BAML and help with syntax guidance.
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
prompting-for-qe
Soạn/tinh chỉnh prompt cho tác vụ QE (sinh test case, phân tích requirement, tóm tắt tài liệu test, phân tích log) — đặc biệt khi output AI lan man, chung chung, bịa, hoặc muốn chốt prompt thành template tái dùng.
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
prompt-evals
Prompt eval fixtures — case design, assertions, versioning, CI gates, no PII in golden data.