cosmos3-inference

cosmos3-inference is a skill for Claude Code, Codex from nebius/nebius-physical-ai. It costs 40 tokens per session (1,760 once invoked), scanned A, original, Apache-2.0.

A guide for running and modifying Cosmos3 inference through NPA. Cosmos3 is NVIDIA's system for generating images or videos from text, images, or videos.

In plain words
What is it for?
Use it to run Cosmos3 image or video generation, change inference defaults, check prompt behavior, or connect NPA workflows to Cosmos documentation.
Why use it?
It explains the supported workflow, input handling, prompts, guardrails, and inference settings in one place.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run Cosmos3 image or video generation, change inference defaults, check prompt behavior, or connect NPA workflows to Cosmos documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nebius/nebius-physical-ai/cosmos3-inference
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 cosmos3-inference
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.

agentmods badge for cosmos3-inference

README.md
[![agentmods](https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-inference/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-inference)
Your own site
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-inference"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-inference/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 cosmos3-inference

Your own site · 80×15
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-inference"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-inference.svg" alt="Reviewed on agentmods" width="80" 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 1,760 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00040 $0.01760
Opus 5 $0.00020 $0.00880
Sonnet 5 $0.00008 $0.00352
Haiku 4.5 $0.00004 $0.00176

Measured 4d ago against content hash f8fddca3f992, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cosmos3-inference 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 4d 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/workflows/cosmos3-inference/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cosmos3 Inference

Source And Attribution

Adapted from NVIDIA cosmos-framework skills/workflows/cosmos3-inference/SKILL.md.

Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. Used under OpenMDW-1.1. See skills/LICENSE-NVIDIA-COSMOS3-OPENMDW-1.1 and skills/NOTICE-NVIDIA-COSMOS3.

When To Use

Use this skill when the user wants to generate an image or video with Cosmos3, change inference defaults, verify prompt handling, inspect guardrails behavior, or connect NPA's Cosmos3 workflow to upstream Cosmos framework inference docs. For environment errors, use skills/atomic/cosmos3-env-troubleshoot/SKILL.md.

Real NPA Workflows

Choose the implementation matching the deployment: persistent Nano vLLM-Omni diffusion, containerized framework generation, or the text-to-image smoke.

Persistent Nano diffusion video

Read npa/deploy/cosmos3-nano-video/README.md for the CLI/SDK contracts, image, frame mapping, measured results and reusable commands. nano-video-batch generates a text-to-video segment followed by tail-conditioned continuations. nano-video-augment transforms a complete source MP4 using official Canny edge controls from every corresponding source interval. A continuation result alone does not demonstrate visual augmentation or full source-motion conditioning.

The augmentation client accepts S3 input/output paths at 832×480 and 24 fps, validates the complete media and publishes immutable artifacts with readback. Use the supported sampling/control flags; there is no generic strength or unchecked extra-parameter bag. Later windows use the preceding augmented five-frame RGB tail for continuity and matching original-source edges for structure. Preserve exact effective prompts, control provenance and all joins. Keep actual source, augmented output and synchronized comparison clearly labeled.

nano-video-augment-recover retrieves the same request or retries artifact publication without submitting generation. Preserve the original destination and submission marker after interrupted generation or artifact retrieval; a missing result is ambiguous. Never repeat GPU generation merely to retry an upload. Validate visual change, identity, source motion, contact and temporal joins separately from decode/hash checks, with a prior rubric and disclosed agent/VLM sampling limits. The README's selected settings are measured examples, not universal quality defaults.

Read the full file on GitHub · 175 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. 4d ago Changed · +19 lines · -2 tokens per session f8fddca3f992
  2. 9d ago First seen · 156 lines · 42 tokens per session scan A 1afcf2e47d48

Subscribe to this mod's changes

cosmos3-inference is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 1,760 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 2026-09-03.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens