data

data is a skill for Claude Code, Codex from robium-ai/robium. It costs 153 tokens per session (2,839 once invoked), scanned A, a copy of data, MIT.

A planning guide for choosing where robot-learning data will come from and how it will be organized. The options include existing datasets, computer-generated simulation data, and demonstrations recorded from real robots using teleoperation, meaning remote human control.

In plain words
What is it for?
Use it to choose a data source, plan storage formats and episode structure, and set up dataset versioning for robotics and physical-AI projects.
Why use it?
It helps teams make the data decision before training begins and avoid storing episodes—the individual recorded task runs—in inconsistent or hard-to-version formats.

Skill for Claude CodeCodex

Part of the robium plugin — 72 skills, 1 agent, 6 hooks 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 skills/robium-ai/robium/1.2.2
Any agent
npx skills add robium-ai/robium --skill 1.2.2
Clone the repo
git clone --depth 1 https://github.com/robium-ai/robium

Made for: Claude Code, Codex.

Or install robium, the plugin that ships this one along with the rest of its 72 skills, 1 agent, 6 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.

agentmods badge for data

README.md
[![agentmods](https://agentmods.dev/badge/skills/robium-ai/robium/1.2.2.svg)](https://agentmods.dev/skills/robium-ai/robium/1.2.2)
Your own site
<a href="https://agentmods.dev/skills/robium-ai/robium/1.2.2"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/1.2.2.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,839 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00153 $0.02839
Opus 5 $0.00077 $0.01419
Sonnet 5 $0.00031 $0.00568
Haiku 4.5 $0.00015 $0.00284

Measured 5d ago against content hash 5fb5e9cf612b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data 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 5d 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.

Origin

This is a copy

94% identical to data — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

archive/data/1.2.2/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

data

The data-sourcing umbrella for robium. Before any policy gets trained, something has to decide where the training data comes from — an existing hub dataset, data generated in simulation, or demonstrations collected via teleop on a real robot — and how it will be stored and versioned once it exists. This skill owns that selection and the cross-cutting sourcing rules; it does not own hub mechanics (huggingface), the LeRobotDataset format (lerobot), or the mechanics of generating synthetic data inside a simulator (isaac-sim, gazebo). It also does not own training itself — that is lerobot and isaac-lab's territory.

When to use this skill

  • Starting any robot-learning task and the data source isn't decided yet — this is a required early step for the manipulation vertical, the same way environments is a required early step for reproducibility.
  • The trigger phrases in the description: 'where do we get data', 'training data for the robot', 'dataset for manipulation', 'generate data in sim', 'collect demonstrations'.
  • Planning storage format, episode structure, or dataset versioning before a collection or generation effort starts, not after.
  • Cross-references — go to the sibling skill instead when the question is:
    • Actually pulling, pushing, or browsing a dataset on the Hub → huggingface. This skill decides which dataset or source strategy to use; it does not own hub auth or transfer mechanics.
    • The LeRobotDataset directory/Parquet+MP4 shape, recording CLI, or dataset editing tools → lerobot. This skill decides whether to record real demonstrations at all; lerobot owns how a recording actually happens.
    • The mechanics of generating synthetic data inside a simulator (Replicator, domain randomization, writers) → isaac-sim or gazebo. This skill decides whether sim-generated data is the right call for a task.
    • Training a policy on the data once sourced → lerobot (or isaac-lab for the NVIDIA RL stack).
    • The whole-stack decision this feeds into → architect (routes here).
    • Sourcing test data — worlds, models, sample datasets, fixtures, and goldens for smoke/regression tests → test-assets. This skill owns data that trains policies; test-assets owns data that tests apps.

Read the full file on GitHub · 201 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. 5d ago First seen · 201 lines · 153 tokens per session scan A 5fb5e9cf612b

Subscribe to this mod's changes

data is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 7d ago), licensed MIT. It adds 153 tokens to every session and 2,839 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to data, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

yolo-training

This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a…

fcakyon/claude-codex-settings · 124 tokens

template-autoresearch-project

AutoResearch loop exemplar — deterministic ML candidate evaluation, evidence registries, claim ledgers, artifact manifests, readiness gates.

docxology/template · 30 tokens

doc-to-lora-evaluator

Evaluate whether Doc-to-LoRA is the right path for turning documents into parametric memory, and guide a safe proof-of-concept before investing in a full plugin or training pipeline. Use when a user wants to internalize long documents, reduce repeated context costs, compare Doc-to-LoRA against RAG or long-context…

markoblogo/abvx-agent-skills · 85 tokens

bioinformatics-scientist

Use when a task needs the judgment of a Bioinformatics Scientist — designing a differential-expression or GWAS analysis with correct multiple-testing correction, calling and triaging variants from NGS data using genotype-likelihood confidence rather than raw allele counts, interpreting a BLAST/DIAMOND homology search…

wonsukchoi/domain-experts · 168 tokens

voiceprint-tech

你是一位声纹识别系统架构师,以《声纹技术》的工程视角帮助用户完成从算法选型到产品落地的技术决策。声纹识别的成败不只在模型结构,更在预处理、后端评分、部署架构与反欺诈的完整链路。.

kuhung/weread-book-skills · 126 tokens

pytorch-training-loop

Use when writing or reviewing a PyTorch training loop. Covers correct train/eval modes, gradient handling, mixed precision, checkpointing, reproducibility, and device management.

param087/agent-ml-skills · 39 tokens