quickstart

quickstart is a command for Claude Code from voxel51/fiftyone-skills. It costs 29 tokens per session (709 once invoked), scanned A, original, Apache-2.0.

A guided first-use command for FiftyOne, a tool for importing, running models on, and viewing computer-vision datasets. It offers separate paths for dataset users and plugin developers.

In plain words
What is it for?
Use it to import datasets, run object-detection models, view results in the FiftyOne App, or start developing a plugin.
Why use it?
It helps newcomers choose a starting workflow and checks whether FiftyOne is connected before they begin.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fiftyone-skills plugin — 18 skills, 2 commands, 1 MCP server shipped together

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 commands/voxel51/fiftyone-skills/quickstart
Clone the repo
git clone --depth 1 https://github.com/voxel51/fiftyone-skills

Made for: Claude Code.

Or install fiftyone-skills, the plugin that ships this one along with the rest of its 18 skills, 2 commands, 1 MCP server.

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 quickstart

README.md
[![agentmods](https://agentmods.dev/badge/commands/voxel51/fiftyone-skills/quickstart.svg)](https://agentmods.dev/commands/voxel51/fiftyone-skills/quickstart)
Your own site
<a href="https://agentmods.dev/commands/voxel51/fiftyone-skills/quickstart"><img src="https://agentmods.dev/badge/commands/voxel51/fiftyone-skills/quickstart.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 709 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00029 $0.00709
Opus 5 $0.00015 $0.00354
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 6d ago against content hash 4aa66dd85038, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quickstart 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.

commands/quickstart.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FiftyOne Quickstart

Welcome to FiftyOne! This quickstart will guide you through your first workflow.

Prerequisites Check

First, let me verify your setup by listing available datasets:

Use the list_datasets MCP tool to check the connection.

If this fails, run:

pip install fiftyone-mcp-server

Then check /fiftyone:help for environment configuration.


Choose Your Path

Option 1: User Quickstart

Build and explore a computer vision dataset.

Step 1: Load a Dataset

You can either:

  • Use the quickstart dataset (built-in):

    Load the FiftyOne quickstart dataset
    
  • Import your own dataset:

    Use /fiftyone:fiftyone-dataset-import to import my dataset from /path/to/data
    
  • Import from Hugging Face Hub:

    Use /fiftyone:fiftyone-dataset-import to import the dataset from huggingface.co/datasets/username/dataset-name
    

Step 2: Run Model Inference

Apply a model to your dataset:

Use /fiftyone:fiftyone-dataset-inference to run object detection on my dataset

This will run a Zoo model (like YOLO or Faster R-CNN) and add predictions to your samples.

Step 3: Explore in the App

Launch the FiftyOne App to visualize your data and predictions:

Launch the FiftyOne App with my dataset

From here you can:

  • Browse samples and labels
  • Filter by predictions or ground truth
  • Identify model errors

Next Steps

Once you're comfortable, try:

  • /fiftyone:fiftyone-find-duplicates - Clean your dataset
  • /fiftyone:fiftyone-model-evaluation - Evaluate prediction quality
  • /fiftyone:fiftyone-embeddings-visualization - Explore data distribution
  • /fiftyone:fiftyone-create-notebook - Generate a full ML pipeline notebook

Option 2: Developer Quickstart

Create a custom FiftyOne plugin.

Step 1: Start Plugin Development

Use /fiftyone:fiftyone-develop-plugin to create a new plugin

The skill will guide you through:

  1. Defining your plugin's purpose
  2. Choosing between operators (actions) or panels (UI)
  3. Generating the plugin structure
  4. Installing and testing locally

Read the full file on GitHub · 121 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. 6d ago First seen · 121 lines · 29 tokens per session scan A 4aa66dd85038

Subscribe to this mod's changes

quickstart is a command published in the GitHub repository voxel51/fiftyone-skills (39 stars, last pushed 20d ago), licensed Apache-2.0. It adds 29 tokens to every session and 709 once invoked, about $0.0001 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.