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.
npx skills add nebius/nebius-physical-ai --skill cosmos3-ray-servegit clone --depth 1 https://github.com/nebius/nebius-physical-aiWrote 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.
[](https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-ray-serve)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-ray-serve"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-ray-serve/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.
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/cosmos3-ray-serve"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/cosmos3-ray-serve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.02117 |
| Opus 5 | $0.00031 | $0.01059 |
| Sonnet 5 | $0.00012 | $0.00423 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
cosmos3-ray-serve 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cosmos3 Native Ray Serve
Use this service for repeated or batched synthetic-data generation where loading
Cosmos3-Nano once is materially better than starting one cosmos3 generate job
per sample. Do not substitute npa-cosmos3-serving: that image serves
Cosmos3-Super through vLLM-Omni and has a different model/API/runtime contract.
Non-negotiable contract
- Run NVIDIA cosmos-framework at pinned commit
5e67049cd94acb667786f1e6dd0dab821cb90c97. - Bind upstream
OmniModelDeployment; its@ray.serve.batchmethod must own coalescing and callOmniInference.generate_batch. - Keep guardrails on unless the operator explicitly opts out.
- Fetch Cosmos3-Nano, VAE, and guardrail weights only at runtime with the operator's access. Use the standard NPA model-cache mount; never bake caches.
- Require
NPA_COSMOS3_RAY_TOKENfor every API endpoint. - Move batch inputs and outputs through S3. Never transfer data directly from a sibling workbench service.
Preflight
Before provisioning or starting GPUs:
npa/.venv/bin/npa workbench health preflight --checks hf,ngc,s3 --json
npa/.venv/bin/npa workbench health access --capability cosmos3 --json
npa/.venv/bin/npa workbench golden-eval show cosmos3-ray-serve
Treat S3 failure, missing Cosmos-Guardrail1 access, or an unpullable exact
image digest as a stop condition. A token's presence is not model entitlement.
Start the service
Run the image by immutable digest, mount /outputs and the standard model cache,
and inject HF_TOKEN and NPA_COSMOS3_RAY_TOKEN as runtime secrets. The image's
default entrypoint starts:
npa workbench cosmos3 ray-serve --world-size 1 --max-batch-size 4
Configuration is explicit: --world-size sets GPUs per replica;
--max-batch-size and --batch-wait-timeout-s are upstream batching knobs;
the service sets Ray's model-replica request admission capacity to the configured
maximum batch size so batches above Ray 2.58's default capacity can form;
--parallelism-preset is the Cosmos placement preset; and
--guardrails/--no-guardrails is the explicit safety posture.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +2 lines 0dde4c92848a
- 2d ago Changed · +46 lines 699147302a40
- 3d ago Changed · +25 lines 5b3aade65329
- 11d ago First seen · 103 lines · 62 tokens per session scan A 27affe0f03e6
cosmos3-ray-serve is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 2,117 once invoked, about $0.0003 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.
Other skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.