fiftyone-skills: Instructions file for Codex

AGENTS.md

fiftyone-skills AGENTS.md is an instructions file for Codex, OpenCode from voxel51/fiftyone-skills. It costs 5,844 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for FiftyOne computer-vision workflows. FiftyOne is a tool for viewing and evaluating image or video datasets, and these instructions cover importing, exporting, and model evaluation.

In plain words
What is it for?
Importing datasets from local files or the Hugging Face Hub, exporting datasets, evaluating computer-vision models, and validating imported samples.
Why use it?
They give an agent a defined process for finding dataset formats, loading data, checking the result, and using the required supporting tools.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: names the NotebookEdit tool; mentions Claude Code; mentions Codex.

This is voxel51/fiftyone-skills's own configuration. It tells Codex and OpenCode how to work on fiftyone-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fiftyone-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to voxel51/fiftyone-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/voxel51/fiftyone-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/voxel51/fiftyone-skills

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 fiftyone-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/voxel51/fiftyone-skills/agents-md/github.svg)](https://agentmods.dev/instructions/voxel51/fiftyone-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/voxel51/fiftyone-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/voxel51/fiftyone-skills/agents-md/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.

agentmods 80×15 button for fiftyone-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/voxel51/fiftyone-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/voxel51/fiftyone-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,844 This file is loaded in full into every session.
When invoked 5,844 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05844 $0.05844
Opus 5 $0.02922 $0.02922
Sonnet 5 $0.01169 $0.01169
Haiku 4.5 $0.00584 $0.00584

Measured 9d ago against content hash 741985aa3152, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fiftyone-skills 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 9d 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 · 598 lines

How it starts

The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FiftyOne Skills - Agent Instructions

This repository contains skills for computer vision workflows using FiftyOne and the FiftyOne MCP Server.

Available Skills

FiftyOne Dataset Import (fiftyone-dataset-import/)

When to use: User wants to import datasets from local files, Hugging Face Hub, or any supported format (COCO, YOLO, VOC, KITTI, etc.), including multimodal grouped datasets.

Instructions: Load the skill file at skills/fiftyone-dataset-import/SKILL.md

Key requirements:

  • FiftyOne MCP server must be running
  • @voxel51/io plugin for importing data
  • @voxel51/utils plugin for dataset management
  • huggingface_hub package for HF Hub imports

Workflow summary:

  1. Scan directory or HF Hub to detect media and labels
  2. Auto-detect format (COCO, YOLO, VOC, parquet, FiftyOne, etc.)
  3. Confirm findings with user
  4. Create dataset and import samples
  5. For HF Hub: use load_from_hub() or snapshot_download()
  6. Validate import count
  7. Launch App to view

Supported sources:

  • Local directories with media files
  • COCO, YOLO, VOC, KITTI, CVAT annotations
  • Hugging Face Hub (FiftyOne-formatted, parquet, or raw formats)
  • Multimodal grouped datasets (autonomous driving)

FiftyOne Dataset Export (fiftyone-dataset-export/)

When to use: User wants to export datasets to standard formats, share on Hugging Face Hub, convert between formats, or create training data archives.

Instructions: Load the skill file at skills/fiftyone-dataset-export/SKILL.md

Key requirements:

  • FiftyOne MCP server must be running
  • @voxel51/io plugin for exporting data
  • huggingface_hub package for HF Hub exports

Workflow summary:

  1. Load dataset and review with dataset_summary()
  2. Confirm export format and destination
  3. For local: use export_samples operator
  4. For HF Hub: use push_to_hub() function
  5. Verify exported file counts

Supported destinations:

  • Local directories (COCO, YOLO, VOC, CVAT, CSV, etc.)
  • Hugging Face Hub (public or private repos)
  • FiftyOne Dataset format (full backup with brain runs)

Read the full file on GitHub · 598 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. 9d ago First seen · 598 lines · 5,844 tokens per session scan A 741985aa3152

Subscribe to this mod's changes

fiftyone-skills AGENTS.md is an instructions file published in the GitHub repository voxel51/fiftyone-skills (39 stars, last pushed 23d ago), licensed Apache-2.0. It adds 5,844 tokens to every session, about $0.0292 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens