What is super-mario-runner?

A browser arcade game that automatically runs and jumps while using the current Claude Code session's activity to drive the game.

It is for launching the Super Mario Runner game in a browser, optionally on a chosen local port, when the user explicitly asks for it.

It gives you a visual way to watch a coding session's token use, tool calls, and context use. It removes the need to inspect those session details as plain numbers.

super-mario-runner — Skill for Claude Code by jaipatel248

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add jaipatel248/claude-arcade

Claude Code

/plugin install claude-arcade

Made for: Claude Code.

Or install claude-arcade, the plugin that ships this one along with the rest of its 1 skill, 12 hooks.

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/skills/jaipatel248/claude-arcade/super-mario-runner/github.svg)](https://agentmods.dev/skills/jaipatel248/claude-arcade/super-mario-runner)

Your own site

<a href="https://agentmods.dev/skills/jaipatel248/claude-arcade/super-mario-runner"><img src="https://agentmods.dev/badge/skills/jaipatel248/claude-arcade/super-mario-runner/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/skills/jaipatel248/claude-arcade/super-mario-runner"><img src="https://agentmods.dev/badge/skills/jaipatel248/claude-arcade/super-mario-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 494 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00062	$0.00494
Opus 5	$0.00031	$0.00247
Sonnet 5	$0.00012	$0.00099
Haiku 4.5	$0.00006	$0.00049

Measured 10d ago against content hash 702380919851, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

super-mario-runner 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 10d 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.

plugins/claude-arcade/skills/super-mario-runner/SKILL.md · 44 lines

What it actually says

Super Mario Runner

Launch the Super Mario Runner arcade game in your browser. Auto-detects the current Claude Code session and locks the visualization to it.

Instructions

The user may provide a port number as the skill argument (e.g. /claude-arcade:super-mario-runner 4000).

Validate the port if provided. It must be an integer between 1024 and 65535. If invalid, tell the user: "Port must be a number between 1024 and 65535." and stop.
Launch the game. The launcher self-daemonizes (forks itself into the background) and works on macOS, Linux, and Windows — no shell backgrounding tricks needed. Run one of these via the Bash tool:

With a port:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/super-mario-runner.js" --port PORT_NUMBER
```
Default port (3248):
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/super-mario-runner.js"
```
If the server is already running on that port, it just reopens the browser tab.
Tell the user it's running. Use this exact message (substitute PORT for the actual port — default 3248):
Super Mario Runner is now open in your browser at http://localhost:PORT/. The character auto-runs and auto-jumps based on this session's token throughput. To stop the server, run /claude-arcade:super-mario-runner with --stop, or:
```
node "${CLAUDE_PLUGIN_ROOT}/scripts/super-mario-runner.js" --stop --port PORT
```

Troubleshooting

Port already in use by another app: Re-run the skill with a different port.
Server didn't start: Run the script with --foreground to see errors directly in the terminal.

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.

10d ago First seen · 44 lines · 62 tokens per session scan A 702380919851

Subscribe to this mod's changes

super-mario-runner is a skill published in the GitHub repository jaipatel248/claude-arcade (6 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 494 once invoked, about $0.0003 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.

Browser automation Claude Code Game development claude claude-code-plugin claude-plugin

search

Search Google, Bing, Amazon, Walmart, YouTube, Google Maps, Google Scholar, and 100+ other engines via the SerpApi REST API. Calls the API using curl. Use when the user wants to search the web, find products or prices, look up local businesses, research academic papers, check news, find jobs, compare flights or…

serpapi/serpapi-claude-plugin · 86 tokens

lab

Instala, inicia, abre, verifica ou encerra o Cannonball 3D Lab local. Use quando o usuário invocar /lab ou pedir para abrir o laboratório 3D do Cannonball em localhost:5555.

harebeats/cannonball · 48 tokens

safari-extension-control-workflow

Guide macOS Safari integration decisions across Safari Web Extensions, Safari Web Inspector Extensions, Safari App Extensions, SafariServices APIs, content blockers, extension messaging, and app-to-Safari control surfaces. Use when the user wants a Mac app to extend, message, open, inspect, debug, or coordinate with…

gaelic-ghost/socket · 91 tokens

browser-use

Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.

Kripu77/software-factory · 40 tokens

safari-mcp-workflow

Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.

gaelic-ghost/socket · 48 tokens

browser-validator

Automatically validate implementations in real browsers after code is written or when user says "test this", "test what you built in the browser", "check it in a real browser", or "validate at the breakpoints". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility…

kanopi/cms-cultivator · 99 tokens