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.
npx agentmods add instructions/rumi-chan/league-client-mcp/copilot-instructionsgit clone --depth 1 https://github.com/rumi-chan/league-client-mcpWrote 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/rumi-chan/league-client-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/rumi-chan/league-client-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/rumi-chan/league-client-mcp/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.04371 | $0.04371 |
| Opus 5 | $0.02185 | $0.02185 |
| Sonnet 5 | $0.00874 | $0.00874 |
| Haiku 4.5 | $0.00437 | $0.00437 |
Grade A, and why
league-client-mcp copilot-instructions.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 6d 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
League Client MCP — Agent Instructions
You are connected to a live League of Legends Client via the league-client-mcp MCP server.
The server bridges tool calls to a Pengu Loader plugin running inside the LoL Client (CEF/Chromium)
over WebSocket at ws://127.0.0.1:8080. All tools communicate synchronously.
Architecture
GitHub Copilot ──MCP stdio──► MCP Server (Node.js)
│ WebSocket ws://127.0.0.1:8080
▼
Pengu Loader Plugin (inside LoL Client)
│ DOM · CSS · JS · LCU fetch()
▼
League of Legends Client (CEF / Chromium / Ember.js)
Prerequisites: League of Legends must be running with Pengu Loader active. The plugin auto-connects on client load. All 16 tools are unavailable until the plugin connects.
Core Workflow
The primary use case is Pengu Loader plugin and theme development:
1. get_lol_dom_snapshot → map the current page (selectors, hierarchy)
2. inject_lol_css → prototype a style change instantly
3. query_lol_element → verify a selector / computed style
4. inject_lol_plugin → add JS behaviour alongside CSS
5. reload_lol_plugin → iterate after updating code
6. export_plugin_to_pengu → persist the finished plugin to disk
7. reload_lol_client → activate the exported plugin permanently
Tool Reference
DOM Inspection
get_lol_dom_snapshot — Sanitized HTML snapshot of the active page. SVG paths, data-*
attributes, inline event handlers, and long src/href values are stripped.
Start every session here. No parameters.
query_lol_element — Tag, text content, bounding rect, computed styles for one element.
Use after you know the selector to verify it — faster than a full snapshot.
| Parameter | Type | Description |
|---|---|---|
selector |
string |
CSS selector |
index |
number? |
Which match to inspect (default 0) |
attributes |
string[]? |
Additional HTML attributes to read |
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.
- 6d ago First seen · 393 lines · 4,371 tokens per session scan A d264f47f90b1
league-client-mcp copilot-instructions.md is an instructions file published in the GitHub repository rumi-chan/league-client-mcp (20 stars, last pushed 5mo ago), licensed MIT. It adds 4,371 tokens to every session, about $0.0219 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 2026-08-30.
Other instructions, from other repositories
AFK CLAUDE.md
Instructions for LilMGenius/AFK, covering afk — claude code project, what this project is, how to use, coach mode (advise only) and play mode (autonomous).
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).