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/ohah/react-native-mcpWrote 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/ohah/react-native-mcp/behavioral-guidelines)<a href="https://agentmods.dev/rules/ohah/react-native-mcp/behavioral-guidelines"><img src="https://agentmods.dev/badge/rules/ohah/react-native-mcp/behavioral-guidelines/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/ohah/react-native-mcp/behavioral-guidelines"><img src="https://agentmods.dev/badge/rules/ohah/react-native-mcp/behavioral-guidelines.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 | $0.00734 | $0.00734 |
| Opus 5.5 | $0.00294 | $0.00294 |
| Sonnet 5.5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
behavioral-guidelines 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 1mo 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.
What it actually says
행동 가이드라인 (AI/에이전트)
프로젝트별 지시와 함께 적용. CLAUDE.md 기반.
트레이드오프: 속도보다 신중함을 우선한다. 사소한 작업은 판단해서 적용한다.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- 구현 전에 가정을 명시한다. 불확실하면 묻는다.
- 해석이 여러 가지면 하나만 골라 쓰지 말고 옵션을 제시한다.
- 더 단순한 방법이 있으면 말한다. 필요하면 반론한다.
- 애매하면 멈추고, 무엇이 애매한지 말한 뒤 질문한다.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- 요청된 범위 밖의 기능은 넣지 않는다.
- 한 번만 쓰는 코드에 추상화를 만들지 않는다.
- 요청되지 않은 "유연성"이나 "설정 가능성"을 넣지 않는다.
- 일어날 수 없는 상황용 예외 처리를 하지 않는다.
- 200줄로 쓸 것을 50줄로 쓸 수 있으면 다시 쓴다.
스스로 묻기: "시니어가 과하다고 할까?" 그렇다면 단순화한다.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
기존 코드 수정 시:
- 인접 코드·주석·포맷을 "개선"하지 않는다.
- 깨진 것이 아닌 코드는 리팩터하지 않는다.
- 기존 스타일에 맞춘다 (본인이 다르게 하더라도).
- 관련 없는 죽은 코드를 발견하면 지우지 말고 언급만 한다.
내 변경으로 미사용이 된 것만:
- 내가 만든 미사용 import/변수/함수는 제거한다.
- 원래 있던 죽은 코드는 요청받기 전에는 제거하지 않는다.
검증: 바꾼 모든 줄이 사용자 요청에 직접 대응해야 한다.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
작업을 검증 가능한 목표로 바꾼다:
- "검증 추가" → "잘못된 입력에 대한 테스트를 쓰고, 통과시킨다"
- "버그 수정" → "재현 테스트를 쓰고, 통과시킨다"
- "X 리팩터" → "리팩터 전후로 테스트가 통과하는지 확인한다"
여러 단계 작업은 짧은 계획을 세운다:
- [단계] → 검증: [체크]
- [단계] → 검증: [체크]
- [단계] → 검증: [체크]
명확한 성공 기준이 있으면 스스로 반복할 수 있다. 모호한 기준("돌아가게 해줘")은 계속 확인이 필요하다.
이 가이드가 잘 적용되면: 불필요한 diff 감소, 과한 구현으로 인한 재작성 감소, 실수 후가 아니라 구현 전에 질문이 나온다.
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.
- 1mo ago First seen · 72 lines · 734 tokens per session scan A 73ea4daf75ad
behavioral-guidelines is a cursor rule published in the GitHub repository ohah/react-native-mcp (7 stars, last pushed 7mo ago), licensed MIT. It adds 734 tokens to every session, about $0.0029 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).