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 skills/this-hw/claude-code-kit/mcp-buildernpx skills add This-HW/claude-code-kit --skill mcp-buildergit clone --depth 1 https://github.com/This-HW/claude-code-kitWhat 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 | $0.00028 | $0.01040 |
| Opus 5 | $0.00014 | $0.00520 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade B, and why
mcp-builder scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Builder
Model Context Protocol 서버 개발 및 구성
MCP 서버를 생성하고 Claude Code에 통합합니다.
사용법
신규 MCP 서버 생성
/mcp-builder "파일 시스템 접근" filesystem
/mcp-builder "데이터베이스 조회" database-query
/mcp-builder "API 통합" external-api
기존 MCP 서버 설정
/mcp-builder setup postgres
/mcp-builder configure playwright
MCP 서버 유형
1. Tools 서버
외부 도구 및 API 접근:
- 데이터베이스 쿼리
- 파일 시스템 조작
- 외부 API 호출
- 시스템 명령 실행
2. Resources 서버
정적 리소스 제공:
- 문서 검색
- 설정 파일 읽기
- 템플릿 제공
3. Prompts 서버
사전 정의된 프롬프트:
- 재사용 가능한 질의
- 템플릿 프롬프트
개발 워크플로우
1. 프로젝트 초기화
# Python MCP 서버
mkdir mcp-server-myproject
cd mcp-server-myproject
python -m venv venv
source venv/bin/activate
pip install mcp
2. 서버 구조 생성
mcp-server-myproject/
├── src/
│ ├── __init__.py
│ └── server.py # MCP 서버 구현
├── pyproject.toml # 의존성
└── README.md # 사용법
3. Tools 정의
from mcp import Server, Tool
server = Server("myproject-server")
@server.tool()
async def my_tool(arg1: str, arg2: int) -> str:
"""도구 설명"""
# 구현
return result
4. 서버 실행
if __name__ == "__main__":
server.run()
Claude Code 통합
1. MCP 설정 파일 수정
~/.claude/settings.json:
{
"mcpServers": {
"myproject": {
"command": "python",
"args": ["-m", "mcp_server_myproject"],
"env": {
"API_KEY": "your-key"
}
}
}
}
2. 서버 시작
claude mcp list # MCP 서버 목록 확인
claude mcp restart # 서버 재시작
템플릿
Python MCP Tools 서버
from mcp import Server
from typing import Any
server = Server("example-server")
@server.tool()
async def example_tool(
param1: str,
param2: int = 10
) -> dict[str, Any]:
"""
Example tool description.
Args:
param1: First parameter
param2: Second parameter (default: 10)
Returns:
Result dictionary
"""
return {
"result": f"Processed {param1} with {param2}",
"status": "success"
}
if __name__ == "__main__":
server.run()
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.
- 2d ago First seen · 236 lines · 28 tokens per session scan B 744272c1c8fa
mcp-builder is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 1,040 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.