What is maxpreps-mcp CLAUDE.md?

Project instructions for maxpreps-mcp, a read-only server that reads public MaxPreps data routes. It documents how roster and schedule data are encoded and checked.

Use it when modifying, reviewing, or testing the maxpreps-mcp repository, especially its data decoding and validation.

It prevents changes from adding unsupported authentication and warns about decoded data that can look correct while using the wrong field names.

How chrischall/maxpreps-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/maxpreps-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/chrischall/maxpreps-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chrischall/maxpreps-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/chrischall/maxpreps-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/maxpreps-mcp/claude-md)

Your own site

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

Per session 551 This file is loaded in full into every session.

When invoked 551 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	$0.00551	$0.00551
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 4ca739596a60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maxpreps-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 · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

maxpreps-mcp

Read-only MCP server over MaxPreps' public Next.js data routes. No credentials anywhere in this repo — no API key, no cookie, no OAuth, no browser bridge. If a change starts introducing an auth path, that is a sign something has gone wrong.

The one thing that makes this repo unusual

Two payloads — team rosters (pageProps.athleteData) and team schedules (pageProps.contests) — arrive as bare positional arrays with the field names stripped. src/decode.ts carries the three key lists lifted verbatim from MaxPreps' own JS bundle and applies them the way the site does.

A shifted key list still produces plausible-looking JSON. Nothing about a misaligned decode looks wrong on inspection: you get strings where strings belong and numbers where numbers belong, just attached to the wrong names. So alignment is never verified by reading the output. It is verified against independent published values, and both checks live in tests/decode.test.ts:

Non-deleted roster rows must equal what the page actually renders.
Summing decoded per-game scores must reproduce the season totals MaxPreps publishes in standingsData.overallStanding — record, points for, points against — for two different schools, states and sports.

If you touch decode.ts, those tests are the gate. Do not relax them to green; re-derive the key lists from the bundle instead (docs/MAXPREPS-API.md has the extraction commands).

Data facts that mislead

resultString is winner-first: a loss reads "L 20-13" when the team scored 13. Always expose teamScore / opponentScore instead.
isDeleted is set on a large minority of roster and contest rows and the site hides them. Unfiltered counts are wrong, not thorough.
An empty current season is normal before opening day — not a failure to report.
homeAwayType: 0 home, 1 away. classYear: numeric 9–12.

Scope

The statewide scoreboard (/<st>/<sport>/scores/) has no server-rendered payload; per-team schedules are the supported route to scores. Don't add a tool that claims otherwise.

Read the full file on GitHub · 47 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 · 47 lines · 551 tokens per session scan A 4ca739596a60

Subscribe to this mod's changes

maxpreps-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/maxpreps-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 551 tokens to every session, about $0.0022 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.

maxpreps-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
maxpreps-mcp CLAUDE.mdchrischall/maxpreps-mcp	Instructions file	0	2d ago	MIT	A	551	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

maxpreps-mcp: Instructions file for Claude Code