agentmods.dev

lol-mcp-server AGENTS.md

lol-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from rexlManu/lol-mcp-server. It costs 1,824 tokens per session, scanned A, original, MIT.

A set of instructions for developing the lol-mcp-server, a TypeScript server that provides League of Legends player analysis, match reviews, and training plans.

In plain words
What is it for?
Use it to install dependencies, run type checks and builds, develop the server, and run unit or live Riot API integration tests.
Why use it?
It gives contributors the project setup, required environment variable, development commands, and testing rules in one place.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

not rated 0 3d ago A scan 1,824 tokens original MIT
View the source file rexlManu/lol-mcp-server
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/rexlmanu/lol-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/rexlManu/lol-mcp-server

Made for: Codex, OpenCode.

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 lol-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rexlmanu/lol-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/rexlmanu/lol-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rexlmanu/lol-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/rexlmanu/lol-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,824 This file is loaded in full into every session.
When invoked 1,824 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01824 $0.01824
Opus 5 $0.00912 $0.00912
Sonnet 5 $0.00365 $0.00365
Haiku 4.5 $0.00182 $0.00182

Measured 5d ago against content hash c0764436c055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lol-mcp-server AGENTS.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 5d 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.

AGENTS.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

TypeScript MCP (Model Context Protocol) server exposing 35 tools for League of Legends player analysis, match review, and training-plan generation. Uses Riot API for live data, Data Dragon for static game data, and Lolalytics/League Wiki scraping for builds and meta.

Key technologies: TypeScript (strict), Node.js 20+, @modelcontextprotocol/sdk, zod, cheerio, vitest, pnpm.

Setup Commands

pnpm install
cp .env.example .env   # Add RIOT_API_KEY=your_key

Riot API key: https://developer.riotgames.com/ (free dev key works).

Development Workflow

  • Dev server: pnpm dev (tsx, hot-reload via stdio)
  • Type check: pnpm typecheck
  • Build: pnpm build (output: dist/)
  • Don't run pnpm dev — assume it's already running if needed.

Testing Instructions

Unit tests (no API key required, run on CI):

pnpm test

Excludes tests/tools.test.ts by default. These are pure logic tests: regions, cache, analysis engines, lolalytics parser, tool schema validation.

Integration tests (require RIOT_API_KEY in .env):

pnpm test:integration

Tests all 35 tools against the real Riot API using account Justice Is Dead#LOTM on EUW and champion Jinx. Never run these on CI — they need a valid API key and network access.

Test files:

  • tests/regions.test.ts — Region routing maps
  • tests/cache.test.ts — TTL cache
  • tests/analysis.test.ts — Performance/champion analysis engines (mocked matches)
  • tests/lolalytics-parser.test.ts — HTML parser
  • tests/review-tools.test.ts — Review tool schemas
  • tests/tools.test.ts — Integration tests (excluded from CI)

Global timeout: 10s per test (see vitest.config.ts).

Before committing: Always run pnpm typecheck && pnpm test && pnpm build.

Code Style

  • TypeScript strict mode — no any unless 100% necessary
  • ESM modules ("type": "module") — all imports use .js extensions
  • zod v3 for all MCP tool input validation (not v4 — breaking changes)
  • camelCase for functions/variables, PascalCase for types/interfaces
  • No comments unless explicitly requested
  • Tool naming: lol_get_*, lol_analyze_*, lol_compare_*
  • File org: src/tools/ (MCP tools), src/riot/ (API client), src/analysis/ (engines), src/static-data/, src/lolalytics/, src/cache/

Read the full file on GitHub · 135 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. 5d ago First seen · 135 lines · 1,824 tokens per session scan A c0764436c055

Subscribe to this mod's changes

lol-mcp-server AGENTS.md is an instructions file published in the GitHub repository rexlManu/lol-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 1,824 tokens to every session, about $0.0091 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.

aianalysiscoachingleague-of-legendslolmcp
Related

Other instructions, from other repositories

Legends-Of-Heroes AGENTS.md

Instructions for FlameskyDexive/Legends-Of-Heroes, covering agents.md, 最小入口规则, 两套技能体系分工, unity 交互入口优先级 and aibridge bootstrap.

FlameskyDexive/Legends-Of-Heroes · 1,139 tokens

AutoRAG AGENTS.md

AGENTS.md instructions for Marker-Inc-Korea/AutoRAG, covering autorag — pi-powered librarian agent, git workflow (binding), before any pr review, pr work, or new feature, after the work is finished and developer commands.

Marker-Inc-Korea/AutoRAG · 4,561 tokens

dsh-deepread AGENTS.md

AGENTS.md instructions for xiehuan123/dsh-deepread, covering agents.md, upstream authority, plugin identities and source files, release documentation and harness lifecycle rules.

xiehuan123/dsh-deepread · 876 tokens

insyra CLAUDE.md

Claude Code instructions for HazelnutParadise/insyra: Read AGENTS.md before doing any project work. Treat it as the project operating contract.

HazelnutParadise/insyra · 25 tokens

TheMAGI CLAUDE.md

Claude Code instructions for Bloodshed-Rain/TheMAGI, covering claude.md, project overview, commands, architecture and process model (electron).

Bloodshed-Rain/TheMAGI · 3,439 tokens

league-client-mcp AGENTS.md

Instructions for rumi-chan/league-client-mcp, covering league client mcp — agent instructions, architecture, standard workflow, tool reference and dom inspection.

rumi-chan/league-client-mcp · 6,726 tokens