research-cosmos-policy

research-cosmos-policy is a skill for Claude Code, Codex from GrayCodeAI/starling. It costs 40 tokens per session (305 once invoked), scanned A, original, MIT.

A skill for evaluating NVIDIA’s Cosmos Policy, a robot-control model, in LIBERO and RoboCasa, simulated environments for testing robot manipulation.

In plain words
What is it for?
Use it to set up Cosmos Policy and evaluate robot manipulation tasks in LIBERO or RoboCasa, including EGL-based rendering.
Why use it?
It helps run repeatable, headless GPU evaluations without manually piecing together the simulator commands and rendering setup.

Skill for Claude CodeCodex

Part of the starling plugin — 54 skills 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/graycodeai/starling/research-cosmos-policy
Any agent
npx skills add GrayCodeAI/starling --skill research-cosmos-policy
Clone the repo
git clone --depth 1 https://github.com/GrayCodeAI/starling

Made for: Claude Code, Codex.

Or install starling, the plugin that ships this one along with the rest of its 54 skills.

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 research-cosmos-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/graycodeai/starling/research-cosmos-policy.svg)](https://agentmods.dev/skills/graycodeai/starling/research-cosmos-policy)
Your own site
<a href="https://agentmods.dev/skills/graycodeai/starling/research-cosmos-policy"><img src="https://agentmods.dev/badge/skills/graycodeai/starling/research-cosmos-policy.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 305 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 $0.00040 $0.00305
Opus 5 $0.00020 $0.00152
Sonnet 5 $0.00008 $0.00061
Haiku 4.5 $0.00004 $0.00030

Measured 5d ago against content hash 89a8acdc5ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-cosmos-policy 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.

categories/ai-ml/research-cosmos-policy/SKILL.md · 36 lines

What it actually says

Advanced topics

LIBERO command matrix: See references/libero-commands.md RoboCasa command matrix: See references/robocasa-commands.md

Resources

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 · 36 lines · 40 tokens per session scan A 89a8acdc5ba1

Subscribe to this mod's changes

research-cosmos-policy is a skill published in the GitHub repository GrayCodeAI/starling (2 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 305 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

fine-tuning-serving-openpi

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging…

Orchestra-Research/AI-Research-SKILLs · 87 tokens

fine-tuning-openvla-oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying…

Orchestra-Research/AI-Research-SKILLs · 103 tokens

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…

earthtojake/text-to-cad · 111 tokens

dart-io

DART IO: URDF, SDF, MJCF parsers, and dart::io loading.

dartsim/dart · 24 tokens

dart-architecture

DART Architecture: the DART 7 multi-physics, multi-solver, multi-backend simulation pipeline and where each abstraction is owned.

dartsim/dart · 32 tokens