Borrowing it
Nothing to install: this file belongs to michaelfromorg/mcp-yahoo-fantasy. 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/michaelfromorg/mcp-yahoo-fantasy/main/CLAUDE.mdgit clone --depth 1 https://github.com/michaelfromorg/mcp-yahoo-fantasyWrote 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/michaelfromorg/mcp-yahoo-fantasy/claude-md)<a href="https://agentmods.dev/instructions/michaelfromorg/mcp-yahoo-fantasy/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelfromorg/mcp-yahoo-fantasy/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/michaelfromorg/mcp-yahoo-fantasy/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelfromorg/mcp-yahoo-fantasy/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 | $0.01399 | $0.01399 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
mcp-yahoo-fantasy 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 8d 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 — 91 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.
Overview
A single MCP (Model Context Protocol) server, in yahoo/, that wraps the Yahoo
Fantasy Sports API for read and write access across NFL/NHL/NBA/MLB. It is a uv-managed
Python 3.12 package. (The repo previously held an NHL server too; that has been removed and
the project is now Yahoo-only.)
Commands
Run from the repo root unless noted.
- Install deps:
./scripts/setup.sh(wrapscd yahoo && uv sync). - One-time Yahoo login:
cd yahoo && uv run yahoo-login --client-id <id> --client-secret <secret>(out-of-band OAuth: open the printed URL, approve, paste back the verifier code). Writes credentials to.envin the working directory. Flags fall back to env vars /.env/ prompt. - Run the server:
cd yahoo && uv run yahoo(stdio transport). - Debug with the MCP Inspector:
./scripts/debug.sh. - Add a dependency:
cd yahoo && uv add <pkg>(keepspyproject.toml+uv.lockin sync). - Sanity-check tool registration without credentials:
cd yahoo && uv run python -c "import asyncio; from yahoo.server import mcp; print(len(asyncio.run(mcp.list_tools())))"
Environment note: uv lock/uv sync need network; in a sandboxed shell run them with the
sandbox disabled. Redirecting command output to /tmp also fails under the sandbox.
There is no automated test suite. Live behavior can only be exercised with real Yahoo
credentials (a .env written by yahoo-login); without them the server starts and lists
tools but tool calls raise a credentials error.
Architecture
Built on FastMCP (mcp.server.fastmcp). Three modules under src/yahoo/, each a deep
layer hiding one concern:
server.py— theFastMCP("yahoo")instance and ~29@mcp.tool()functions. Tools are intentionally thin: resolve args, call oneclientmethod, return the result. They returnyahoo_fantasy_api's plain dicts/lists, which FastMCP serializes to JSON for the model. Each tool's docstring IS its description shown to the model, so keep them accurate.client.py—YahooClient, the single seam overyahoo_fantasy_api. It owns the OAuth session (lazy), cachesGame/Leagueobjects, and resolves defaults: an omittedleague_keyfalls back to$YAHOO_LEAGUE_KEY; an omittedteam_keyfalls back to the authenticated user's own team (League.team_key()). A module-levelclientsingleton is shared by all tools.auth.py— the OAuth2 bridge plus.envhelpers.yahoo_fantasy_apireads credentials viayahoo_oauth'soauth2.json.auth.session()callsload_env_file()(loads.envinto the environment without clobbering real vars), then bridges$YAHOO_CONSUMER_KEY/ SECRET(+ token vars) into aoauth2.jsonand returns a token-refreshedOAuth2. Credential source priority: existingoauth2.json->.env/env vars. The bridged file is written to~/.config/yahoo-fantasy-mcp/oauth2.json(override path with$YAHOO_OAUTH_FILEor dir with$YAHOO_MCP_CONFIG_DIR);.envdefaults to./.env(override$YAHOO_ENV_FILE).login.py— theyahoo-loginCLI (a[project.scripts]entry point). Runsyahoo_oauth's out-of-band OAuth flow (OAuth2(..., browser_callback=False, store_file=False)), thenwrite_env()s the resulting client id/secret + access/refresh tokens to.envand deletes any staleoauth2.jsonso the server re-bridges from the fresh.env.
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.
- 8d ago First seen · 91 lines · 1,399 tokens per session scan A 8334a82fab66
mcp-yahoo-fantasy CLAUDE.md is an instructions file published in the GitHub repository michaelfromorg/mcp-yahoo-fantasy (6 stars, last pushed 3mo ago), licensed MIT. It adds 1,399 tokens to every session, about $0.0070 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
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).
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).
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.
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.