What is gemini-robotics?

A command-line and Python workflow for planning and evaluating Gemini Robotics 2, a hosted AI system for reasoning about actions in physical environments. It also supports distillation, which trains a smaller student policy from generated demonstrations.

Use it to run embodied-reasoning planning, rubric evaluation, or a teacher-student workflow that generates demonstrations in MuJoCo and trains a PyTorch policy.

It provides a defined way to call the hosted model and evaluate robotics plans without assuming a local model is available.

gemini-robotics — Skill for Claude Code and Codex by nebius

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.

Any agent

npx skills add nebius/nebius-physical-ai --skill gemini-robotics

Clone the repo

git clone --depth 1 https://github.com/nebius/nebius-physical-ai

Made for: Claude Code, Codex.

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/nebius/nebius-physical-ai/gemini-robotics/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/gemini-robotics)

Your own site

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/gemini-robotics"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/gemini-robotics/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/nebius/nebius-physical-ai/gemini-robotics"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/gemini-robotics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 527 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	$0.00032	$0.00527
Opus 5.5	$0.00013	$0.00211
Sonnet 5.5	$0.00006	$0.00105
Haiku 4.5	$0.00003	$0.00053

Measured 10d ago against content hash 2c7b0ab4c86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-robotics 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.

skills/tools/gemini-robotics/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Robotics

Gemini Robotics is the closed-weight VLA tool for ER (embodied reasoning) planning and rubric evaluation, all served through the hosted Gemini API (GOOGLE_API_KEY required).

The toolRefs are a live-validated API adapter: every stage requires an explicit --model (no default). The validated model identifier is documentation only and is never selected by the implementation.

Workflow tasks use the default CPU image with staged NPA source because the adapter calls a hosted API. Pass --secret-env GOOGLE_API_KEY when submitting; the renderer declares that credential hint and does not select a local model image. Explicit API/model overrides remain required. Transport tests do not establish live provider availability.

Interfaces

CLI: npa workbench gemini-robotics <plan|eval|distill> --help
distill: teacher-student loop - ER-2 plans, MuJoCo generates demos, PyTorch behavior-clones a student policy (CUDA when available; run on a Nebius GPU job), MuJoCo evaluates closed-loop. One command, no stubs.
Python SDK (workbench-first): npa.workbench.gemini_robotics (plan, eval — aliases of run_er_planning_stage, run_eval_stage)
Workflow module: npa.workflows.byof.gemini_robotics_pipeline (stage functions, receipt writing, argparse entrypoint)

Conventions

The CLI lives at npa.cli.workbench.gemini_robotics (multi-command package form for new tools); the SDK surface lives at npa.workbench.gemini_robotics and does not go through make_cli_wrapper.
Public workflow inputs and outputs are exact s3:// objects. plan accepts config.task and writes config.output_uri; eval accepts an input_uri JSON object with non-empty plan_text and rubric strings and writes config.output_uri. Eval receipts record the exact input URI, ETag, and SHA-256; all receipts use conditional create and are not overwritten.
Plans and evaluations are advisory only. The adapter does not execute a safety-review tool and does not authorize physical execution.

Read the full file on GitHub · 46 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.

10d ago First seen · 46 lines · 32 tokens per session scan A 2c7b0ab4c86c

Subscribe to this mod's changes

gemini-robotics is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 527 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.

Building agents Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 44 tokens

phylogenetics

Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…

K-Dense-AI/scientific-agent-skills · 71 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

presenting-conference-talks

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Orchestra-Research/AI-Research-SKILLs · 53 tokens