What is kenpom-mcp CLAUDE.md?

A set of Claude Code instructions for a KenPom basketball-data server. KenPom is a website that provides basketball rankings and statistics.

Use it when working on the server, its web-data scraping and parsing code, its local or remote connections, or its tests and code-quality checks.

It gives the coding agent the project's purpose, current status, design, tools, and development practices in one reference.

How dburge86/kenpom-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dburge86/kenpom-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.

Copy the file

curl -O https://raw.githubusercontent.com/dburge86/kenpom-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dburge86/kenpom-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dburge86/kenpom-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dburge86/kenpom-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dburge86/kenpom-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dburge86/kenpom-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dburge86/kenpom-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dburge86/kenpom-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,611 This file is loaded in full into every session.

When invoked 4,611 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.

Model	Per session	Once invoked
Fable 5.1	$0.04611	$0.04611
Opus 5.5	$0.01844	$0.01844
Sonnet 5.5	$0.00922	$0.00922
Haiku 4.5	$0.00461	$0.00461

Measured 2mo ago against content hash f0afbfd8f97a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kenpom-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 2mo 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 · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KenPom MCP Server

Purpose

Production-ready async MCP server that scrapes KenPom basketball analytics and exposes 18 data tools via STDIO (local) and HTTP/SSE (remote) transports.

Project Status: Production Ready ✅

100% test coverage (61 tests)
Automated CI/CD with GitHub Actions
Pre-commit hooks enforcing code quality
Network resilience with retry logic
Unified tool registry (no code duplication)

Tech Stack

Python 3.12+ with uv package manager
FastMCP framework for STDIO transport
Starlette for HTTP/SSE transport
httpx async HTTP client with retry logic (tenacity)
BeautifulSoup4 + lxml for HTML parsing
pytest with pytest-asyncio and pytest-httpx for testing
ruff for linting and formatting
pre-commit for automated quality checks

Architecture

src/kenpom_mcp/
├── server.py          # FastMCP server (STDIO transport)
├── http_server.py     # Starlette server (HTTP/SSE transport)
├── tools.py           # Unified tool registry (18 tools)
├── scraper.py         # Async scraper with auth + retry logic
└── parsers/           # HTML parsers for each KenPom page type

tests/
├── fixtures/          # 14 HTML fixtures for testing
├── test_fixtures.py   # Fixture loading tests (14 tests)
├── test_parsers.py    # Parser unit tests (33 tests)
└── test_scraper.py    # Scraper integration tests (14 tests)

Key Files

src/kenpom_mcp/server.py - FastMCP server with 13 tools (STDIO)
src/kenpom_mcp/http_server.py - Starlette server (HTTP/SSE)
src/kenpom_mcp/tools.py - Unified tool registry (18 tools, single source of truth)
src/kenpom_mcp/scraper.py - Async scraper with retry logic + season validation
src/kenpom_mcp/parsers/ - HTML parsing modules (7 files: ratings, efficiency, stats, misc, fanmatch, team, conference)
tests/ - Test suite (61 tests, 45 passing)
pyproject.toml - Dependencies and project config
.pre-commit-config.yaml - Pre-commit hooks (ruff)
.github/workflows/ci.yml - CI/CD pipeline

Read the full file on GitHub · 421 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.

2mo ago First seen · 421 lines · 4,611 tokens per session scan A f0afbfd8f97a

Subscribe to this mod's changes

kenpom-mcp CLAUDE.md is an instructions file published in the GitHub repository dburge86/kenpom-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 4,611 tokens to every session, about $0.0184 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.

kenpom-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kenpom-mcp CLAUDE.mddburge86/kenpom-mcp	Instructions file	1	9mo ago	MIT	A	4,611	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

kenpom-mcp: Instructions file for Claude Code