Runnywhere-PlayMCP: Instructions file for Claude Code

CLAUDE.md

Runnywhere-PlayMCP CLAUDE.md is an instructions file for Claude Code from Querry-AI/Runnywhere-PlayMCP. It costs 6,453 tokens per session, scanned A, original, MIT.

A set of instructions for working on Runnywhere-PlayMCP, a server that creates running routes and animal-shaped GPS drawings on Seoul’s walking-road network. It documents the project, commands, architecture, tests, and rules the code must follow.

In plain words
What is it for?
Use it when developing, testing, running, load-testing, or packaging the Runnywhere-PlayMCP server.
Why use it?
It helps a coding agent work within the project’s existing design and performance requirements instead of making changes that break its rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Querry-AI/Runnywhere-PlayMCP's own configuration. It tells Claude Code how to work on Runnywhere-PlayMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Runnywhere-PlayMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Querry-AI/Runnywhere-PlayMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Querry-AI/Runnywhere-PlayMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Querry-AI/Runnywhere-PlayMCP

Made for: Claude Code.

Wrote 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.

agentmods badge for Runnywhere-PlayMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/querry-ai/runnywhere-playmcp/claude-md/github.svg)](https://agentmods.dev/instructions/querry-ai/runnywhere-playmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/querry-ai/runnywhere-playmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/querry-ai/runnywhere-playmcp/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.

agentmods 80×15 button for Runnywhere-PlayMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/querry-ai/runnywhere-playmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/querry-ai/runnywhere-playmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,453 This file is loaded in full into every session.
When invoked 6,453 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06453 $0.06453
Opus 5 $0.03227 $0.03227
Sonnet 5 $0.01291 $0.01291
Haiku 4.5 $0.00645 $0.00645

Measured 11d ago against content hash d5fb0bf02c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Runnywhere-PlayMCP 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 11d 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.

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

프로젝트

Runnywhere(러니웨어) — 서울 보행 도로망 위에 러닝 코스와 동물 모양 GPS 아트 코스를 생성하는 MCP 서버. 카카오 PlayMCP 공모전 출품작이며, PlayMCP 심사 기준(stateless, p99 ≤ 3s, avg ≤ 100ms)이 설계 전반을 지배한다. 사용자 대면 텍스트는 전부 한국어, 코드 주석은 영어다. README.md에 데이터 스냅숏·환경변수 전체 목록이 있다.

명령어

source .venv/bin/activate && pip install -e '.[dev]'
python -m runart.server                  # http://localhost:8000/mcp (Streamable HTTP, JSON)
pytest                                   # 전체 (실제 58MB 그래프 로드 — 첫 테스트가 느림)
pytest 'tests/test_shapes.py::test_shape_course_passes_similarity_gate[dog]' -q  # 단일 테스트
pytest -k "zigzag or detour" -q          # 이름으로 골라 실행
python scripts/loadtest.py 1000 10       # 서버 구동 상태에서 부하 테스트
RUNART_LOADTEST_REPORT=artifacts/playmcp-loadtest.json python scripts/loadtest.py 1000 10
docker build -t runnywhere . && docker run -p 8000:8000 -e RUNART_BASE_URL=https://<endpoint> runnywhere

ETL(그래프·RFS·프리셋 재생성)은 pip install -e '.[etl]' 후 README.md "실행" 절의 순서를 그대로 따른다. 오래 걸리고 결과물이 코드의 체크섬과 묶여 있으므로, 요청받지 않았다면 실행하지 않는다.

아키텍처

의존 방향은 단방향이다: geograph/rfs/facilities/infrastructurecourseshapesserver. render·widget·insights·exploration은 표현 계층이고 models는 전역 공유된다. 역방향 import를 만들지 말 것.

  • server.py — MCP 툴 9개 + 웹 라우트 17개를 한 앱에서 서빙. FastMCP stateless_http=True, json_response=True.
  • course.py — 목표 거리의 원주에 waypoint 4개를 놓고 RFS 가중 Dijkstra로 잇는 순환 코스. 여러 bearing을 시도하고 ±5% 안에 들 때까지 원을 rescale. 후보 순위에는 RFS·경사·따라가기 쉬움과 함께 retrace_share(같은 길 되돌아오는 비율)가 들어간다 — 공원 보행망은 격자가 아니라 나무 구조라 이게 없으면 왕복 코스가 뽑힌다.
  • shapes.py — 동물 템플릿(닫힌 폴리라인)을 스케일·회전·스냅한 뒤 유사도 게이트로 판정. 게이트를 못 넘으면 나쁜 코스를 내보내는 대신 거절하고 대안을 제안한다. 게이트 값은 동물마다 다르다(SHAPE_STYLES).
  • rfs.py — 러닝 친화도 점수(6개 항목 가중합) + 라우팅 가중치. night_mode는 별도 프로파일, include_hills는 경사 항을 감점에서 가점으로 뒤집는다.
  • insights.py — 코스가 스스로에 대해 말하는 것(특징 칩·좋은 점·참고할 점). 파생 문장은 전부 코스가 이미 가진 데이터(RFS 성분·누적 오르막·횡단 수·편의시설)에서만 만든다. 성분 임계값은 서울 전역 실측 중앙값 기준이라 절대 수치가 아니다 — 조명은 도시 전체가 무데이터 기본값 0.5 아래라, 고정 컷오프를 쓰면 "조명 어두움"이 네 코스 중 셋에 붙는다.
  • etl/ — 오프라인 파이프라인. 런타임에는 경로·안전·시설 데이터를 위해 외부 API를 절대 호출하지 않는다(지오코딩만 예외).

Read the full file on GitHub · 140 lines

Changes

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.

  1. 11d ago First seen · 140 lines · 6,453 tokens per session scan A d5fb0bf02c6f

Subscribe to this mod's changes

Runnywhere-PlayMCP CLAUDE.md is an instructions file published in the GitHub repository Querry-AI/Runnywhere-PlayMCP (0 stars, last pushed 2d ago), licensed MIT. It adds 6,453 tokens to every session, about $0.0323 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.

Related

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens