Borrowing it
Nothing to install: this file belongs to azureiraraavis-png/plant-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/azureiraraavis-png/plant-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/azureiraraavis-png/plant-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/instructions/azureiraraavis-png/plant-mcp/claude-md)<a href="https://agentmods.dev/instructions/azureiraraavis-png/plant-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/azureiraraavis-png/plant-mcp/claude-md/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/instructions/azureiraraavis-png/plant-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/azureiraraavis-png/plant-mcp/claude-md.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 | $0.01637 | $0.01637 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
plant-mcp CLAUDE.md 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 12d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
이 저장소에서 작업할 때 알아야 할 것들. 다른 기기에서 처음 열었더라도 이 문서만 읽으면 바로 이어서 작업할 수 있도록 작성했다.
무엇인가
반려식물의 물주기·상태를 기록하는 MCP 서버. Claude Desktop에 stdio로 붙어서 사용자가 대화로 식물을 관리한다. 개인 포트폴리오 프로젝트.
src/plant_mcp/storage.py SQLite 저장 계층 — MCP를 전혀 모른다
src/plant_mcp/server.py MCP 서버 — storage를 호출해 툴로 노출
⚠️ mcp SDK 2.0 — 1.x와 API가 다르다
가장 흔한 실수. 학습 데이터에 있는 FastMCP 패턴으로 짜면 동작하지 않는다.
이 프로젝트는 mcp>=2.0.0을 쓴다.
# 이 프로젝트가 쓰는 것 (2.0)
from mcp.server import MCPServer
server = MCPServer(name="plant-care", version="0.1.0", instructions="...")
@server.tool(description="...")
def my_tool(x: int) -> str: ...
@server.resource("plant://{name}", mime_type="application/json")
def my_resource(name: str) -> str: ...
@server.prompt(name="diagnose")
def my_prompt(a: str) -> str: ...
server.run("stdio")
# 1.x 패턴 — 이 프로젝트에 없음. 쓰지 말 것
from mcp.server.fastmcp import FastMCP # ← ImportError
응답 모델 필드는 snake_case다. 카멜케이스로 접근하면 AttributeError가 난다.
| 쓸 것 | 쓰면 안 되는 것 |
|---|---|
init.server_info |
serverInfo |
init.protocol_version |
protocolVersion |
tool.input_schema |
inputSchema |
result.resource_templates |
resourceTemplates |
template.uri_template |
uriTemplate |
server.list_tools() / call_tool() / read_resource() / get_prompt()는
모두 async다. 툴이 예외를 던지면 SDK가 ToolError로 감싸 올린다.
API가 기억과 다르면 추측하지 말고 설치된 패키지를 직접 확인할 것:
uv run python -c "from mcp.server import MCPServer; import inspect; print([n for n in dir(MCPServer) if not n.startswith('_')])"
설계 원칙 (지킬 것)
storage.py는 MCP를 몰라야 한다. 서버 없이 단독 테스트가 가능해야 하고, 나중에 다른 인터페이스를 붙일 여지를 남긴다.- 커넥션은 호출마다 연다. 서버가 툴을 여러 스레드에서 실행해도 안전하도록. 전역 커넥션을 만들지 말 것.
- 파괴적 동작에는 가드를 둔다.
remove_plant는confirm=True없이는 삭제하지 않고 확인 문장만 돌려준다. 새로 추가하는 삭제성 툴도 같은 패턴을 따를 것. - 오류 메시지는 LLM이 재호출로 교정할 수 있게 쓴다. 예: 없는 식물을 조회하면 등록된 식물 목록을 메시지에 포함한다.
- 조회 툴은 구조화된 dict/list를, 기록 툴은 사람이 읽을 문장을 돌려준다. LLM이 결과를 그대로 사용자에게 전달해도 자연스럽도록.
- 파생 상태를 저장하지 않는다.
needs_water는 조회 시점에 계산한다 (마지막 물준 날 + 간격 <= 기준일). 갱신 배치가 필요 없어진다.
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.
- 12d ago First seen · 133 lines · 1,637 tokens per session scan A d2f3bbb234c1
plant-mcp CLAUDE.md is an instructions file published in the GitHub repository azureiraraavis-png/plant-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).