Super Mario Runner

VerifiedCaution

Launch a Super Mario arcade game in your browser, driven by the real-time metrics of the Claude Code session.

Sby Skills Guide Bot
ProductivityBeginner
7/22/2026
Claude Code
#arcade-game#session-visualization#localhost#browser#token-usage

Recommended for

Automated summary

Opens a pixel-art Super Mario arcade game in the browser whose character auto-runs and auto-jumps based on the token throughput, tool calls and context usage of the current Claude Code session.

Strengths

  • Single-command launch via a launcher that self-daemonizes and works on macOS, Linux and Windows
  • Optional port argument with validation (1024–65535) that simply reopens the tab if the server is already up
  • Locks the visualization to the current session with no extra configuration
  • Ships --stop and --foreground options for shutting the server down or debugging a failed start

Limitations

  • Purely decorative: it produces no actionable metrics for real work
  • Requires Node plus the plugin script resolved through CLAUDE_PLUGIN_ROOT, and a local browser
  • Explicit invocation only (disable-model-invocation), so the skill never triggers on its own
When to use it

Use it when you want a fun ambient animation that mirrors the current session's activity.

When not to use it

Avoid it in browserless environments such as CI or headless servers, or when you actually need performance data to analyze.

Security analysis

Caution
Quality score85/100

The skill is not overtly malicious: it validates ports, uses a plugin-root script path, binds locally, and provides stop instructions. However, it launches a background daemon and browser, and relies on session telemetry that could be sensitive if handled improperly. Since the implementation script is not included for inspection, this warrants caution rather than safe.

Findings
  • •Uses the Bash tool to execute a local Node.js script and start a self-daemonizing background server.
  • •Opens a browser tab and binds to localhost, which is legitimate but creates a persistent local process.
  • •Claims to auto-detect and visualize the Claude Code session, implying access to session/token/tool/context data; the actual script contents are not provided, so privacy handling cannot be verified.
  • •No allowed-tools are declared, despite the instructions requiring Bash execution.
How this analysis is made

Examples

Lancer le jeu par défaut
Lance Super Mario Runner dans mon navigateur.
Choisir un port
Open the Mario arcade game on port 4000, please.
Arrêter le serveur
Stop the Super Mario Runner server on port 4000.

name: super-mario-runner description: Open Super Mario Runner — an auto-playing pixel arcade game in the browser, driven by this Claude Code session's real-time token throughput, tool calls, and context usage. Trigger only when the user explicitly asks to start, open, launch, or run the arcade/game/Mario. disable-model-invocation: true

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).

  1. 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.

  2. 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.

  3. 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.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/super-mario-runner-mrwakcuj/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/super-mario-runner-mrwakcuj' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/super-mario-runner-mrwakcuj/download' --output '.skill-downloads/super-mario-runner-mrwakcuj/SKILL.md.part' && mv '.skill-downloads/super-mario-runner-mrwakcuj/SKILL.md.part' '.skill-downloads/super-mario-runner-mrwakcuj/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/super-mario-runner-mrwakcuj/SKILL.md' && test -s '.skill-downloads/super-mario-runner-mrwakcuj/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/super-mario-runner' && cp -R '.skill-downloads/super-mario-runner-mrwakcuj' '.claude/skills/super-mario-runner'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/super-mario-runner-mrwakcuj'

openskills read 'super-mario-runner-mrwakcuj'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/super-mario-runner-mrwakcuj/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills