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.
npx agentmods add rules/lazylagom/context-compose-mcp/mcp-developmentgit clone --depth 1 https://github.com/lazylagom/context-compose-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/lazylagom/context-compose-mcp/mcp-development)<a href="https://agentmods.dev/rules/lazylagom/context-compose-mcp/mcp-development"><img src="https://agentmods.dev/badge/rules/lazylagom/context-compose-mcp/mcp-development.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00799 |
| Opus 5 | $0.00000 | $0.00400 |
| Sonnet 5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
mcp-development 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.
What it actually says
MCP 개발 가이드라인
Model Context Protocol (MCP) 아키텍처
MCP 서버 구조
- 메인 서버: mcp-server/server.ts
- FastMCP 프레임워크: 빠르고 효율적인 MCP 서버 구현
- 도구 등록: MCP 도구들을 서버에 등록하고 관리
핵심 MCP 도구들
- get-context: 프로젝트 컨텍스트 조회
- init: 프로젝트 초기화
MCP 서버 개발 패턴
// MCP 도구 등록 예시
server.tool('tool-name', {
description: '도구 설명',
parameters: {
// Zod 스키마를 사용한 파라미터 검증
}
}, async (params) => {
// 도구 로직 구현
});
CLI와 MCP 서버 통합
이중 진입점 구조
- CLI 진입점:
context-compose→ src/cli/index.ts - MCP 진입점:
context-compose-mcp→ mcp-server/server.ts
공통 핵심 로직 공유
- core 모듈: CLI와 MCP 서버가 공통으로 사용하는 비즈니스 로직
- 타입 안전성: 동일한 TypeScript 타입과 스키마 공유
AI 모델 통합
Claude Desktop 설정
{
"mcpServers": {
"context-compose": {
"command": "context-compose-mcp",
"args": [],
"cwd": "/path/to/project"
}
}
}
MCP 도구 디버깅
- 검사 명령어:
npm run inspect- 개발 중인 MCP 서버 검사 - 빌드된 버전 검사:
npm run inspect:built- 빌드된 MCP 서버 검사
Context 시스템 설계
YAML 기반 컨텍스트
version: 1
kind: task
name: 'feature-development'
description: '새로운 기능 개발을 위한 컨텍스트'
context:
workflow: workflows/feature-workflow.yaml
roles:
- personas/dan-abramov.yaml
rules:
- rules/clean-code.yaml
mcps:
- mcps/sequential-thinking.yaml
사전 정의된 컨텍스트들
- default: 기본 개발 컨텍스트
- feature: 새로운 기능 개발
- fix: 버그 수정
- refactor: 코드 리팩토링
- api: API 개발
- testing: 테스트 작성
- documentation: 문서 작업
- security: 보안 관련 작업
- performance: 성능 최적화
워크플로우 엔진
자동화된 작업 흐름
- 개발, 테스트, 배포 단계 자동화
- 역할 기반 개발 적용
- 알림 시스템과 통합
역할 기반 개발
- 전문가 페르소나: Dan Abramov, Martin Fowler 등
- 컨텍스트별 역할 적용: 각 컨텍스트에 적합한 전문가 관점 제공
테스트 전략
MCP 서버 테스트
- 통합 테스트: MCP 도구들의 정상 동작 검증
- Playwright 테스트: 실제 AI 모델과의 통합 테스트
CLI 테스트
- 단위 테스트: 개별 CLI 명령어 테스트
- E2E 테스트: 전체 워크플로우 테스트
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 · 113 lines · 0 tokens per session scan A a625c77dac3b
mcp-development is a cursor rule published in the GitHub repository lazylagom/context-compose-mcp (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 799 tokens. 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
auth
Auth architecture, middleware chain, and auth-specific coding standards.
tableau-mcp
Tableau MCP project context, architecture overview, and core principles.
tools
MCP tool development patterns — factory pattern, base class, callbacks, and descriptions.
testing
Testing standards — Vitest framework, test organization, mocking patterns.
cursorrules
Cursor rule "cursorrules" from dunialabs/peta-core, covering cursor ide scheduling rules, role positioning, task assignment rules, → assign to claude code (precise, controllable) and → assign to codex (complex, large-scale).
chrono-mcp-standards
Chrono MCP Project Standards and Guidelines.