FPL-MCP: Instructions file for Claude Code

CLAUDE.md

FPL-MCP CLAUDE.md is an instructions file for Claude Code from MoayadAbbara/FPL-MCP. It costs 768 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code when working on an unofficial Fantasy Premier League MCP server. They describe the local Python commands, layered code structure and rules for separating tools, formatting, business logic and the public FPL API.

In plain words
What is it for?
Use them when running the server, installing dependencies, formatting code, running tests, checking available MCP tools or adding FPL features.
Why use it?
They give the coding agent the project’s conventions so changes fit the existing architecture and remain easier to test.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is MoayadAbbara/FPL-MCP's own configuration. It tells Claude Code how to work on FPL-MCP 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 FPL-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MoayadAbbara/FPL-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/MoayadAbbara/FPL-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MoayadAbbara/FPL-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.

agentmods badge for FPL-MCP CLAUDE.md

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

agentmods 80×15 button for FPL-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/moayadabbara/fpl-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/moayadabbara/fpl-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 768 This file is loaded in full into every session.
When invoked 768 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 $0.00768 $0.00768
Opus 5.5 $0.00307 $0.00307
Sonnet 5.5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 2mo ago against content hash fd8e8f853749, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

FPL-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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FPL MCP

An MCP server for Fantasy Premier League. Local-first (stdio): reads the user's team, analyses players, and will manage transfers/captain/chips. Unofficial, uses the public FPL API.

Commands (this project uses uv)

  • Install/sync: uv sync --extra dev
  • Run server: uv run python src/server.py
  • Format + lint: uv run ruff format . && uv run ruff check --fix .
  • Tests: uv run pytest -q
  • Quick tool check: uv run python -c "import sys; sys.path.insert(0,'src'); import asyncio; from server import mcp; print([t.name for t in asyncio.run(mcp.list_tools())])"

Layout

This is an application, not a library ([tool.uv] package = false). Code lives flat under src/ — no src/fpl_mcp/ package wrapper. Running python src/server.py puts src/ on the import path, so modules import as top-level: from api.client import ..., from domain.team import ....

Architecture — layered, each layer only knows the one below

src/
  tools/    MCP tool surface (thin glue: fetch -> domain -> format -> str)
  format/   raw data -> compact, model-friendly TEXT
  domain/   pure FPL logic (dataclasses; knows NO http/mcp) -> easy to test
  api/      FPL HTTP client (httpx). No caching yet — kept simple on purpose.
  auth/     token storage & expiry (token.txt for now)
  config.py central constants (URLs, client_id, TTLs)
  server.py entry point only: build app, register tools, run stdio

Non-negotiable rules

  • Never return raw FPL JSON to the model. bootstrap-static is ~500k tokens; always go through domain/ then format/ and return only decision-relevant fields.
  • domain/ stays pure — no httpx, no mcp imports. It takes dicts, returns dataclasses.
  • Tool names: snake_case, multi-word, ≤8 params. Lightweight output by default; add a detailed=True flag for the verbose view rather than always dumping everything.
  • Read tools in tools/read_tools.py, write tools (transfer/captain/chip) go in tools/write_tools.py when we build them — keep the two separate.

Read the full file on GitHub · 57 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. 2mo ago First seen · 57 lines · 768 tokens per session scan A fd8e8f853749

Subscribe to this mod's changes

FPL-MCP CLAUDE.md is an instructions file published in the GitHub repository MoayadAbbara/FPL-MCP (0 stars, last pushed 2mo ago), licensed MIT. It adds 768 tokens to every session, about $0.0031 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.

Related

FPL-MCP CLAUDE.md compared with instructions from other repositories

FPL-MCP CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
FPL-MCP CLAUDE.mdMoayadAbbara/FPL-MCPInstructions file02mo agoMITA768Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode