agentmods.dev

serve-model

serve-model is a skill for Claude Code, Codex from NVIDIA/deepops. It costs 36 tokens per session (911 once invoked), scanned A, original, BSD-3-Clause.

A workflow for serving a cached AI model on one GPU with vLLM, a tool that runs models behind a text-generation endpoint. It also checks that the local endpoint starts and can answer a request.

In plain words
What is it for?
Use it to start a single-node model server, validate a local completion endpoint, and diagnose startup or inference failures.
Why use it?
It makes the required cache, machine, environment, permissions, and validation checks explicit before reporting that a model is available.

Skill for Claude CodeCodex ✓ vendor

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/validation/validate_vllm.py --json \.

not rated 1.5krepo +2 yesterday A scan 36 tokens original BSD-3-Clause

Good fit Use it to start a single-node model server, validate a local completion endpoint, and diagnose startup or inference failures.

Compare 6 skills from other repositories ↓
View source ↗ NVIDIA/deepops
About the project

DeepOps is a collection of automation tools for deploying and managing compute clusters that use NVIDIA GPUs with Kubernetes or Slurm. It supports environments ranging from full data-center clusters to individual machines needing GPU drivers, Docker, and NVIDIA container support.

NVIDIA/deepops · 1,485 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/NVIDIA/deepops
agentmods
npx agentmods add skills/nvidia/deepops/serve-model

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 serve-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/deepops/serve-model/github.svg)](https://agentmods.dev/skills/nvidia/deepops/serve-model)
Your own site
<a href="https://agentmods.dev/skills/nvidia/deepops/serve-model"><img src="https://agentmods.dev/badge/skills/nvidia/deepops/serve-model/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 serve-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/deepops/serve-model"><img src="https://agentmods.dev/badge/skills/nvidia/deepops/serve-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 911 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00911
Opus 5.5 $0.00014 $0.00364
Sonnet 5.5 $0.00007 $0.00182
Haiku 4.5 $0.00004 $0.00091

Measured yesterday against content hash 26b76d30463a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

serve-model 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.

skills/serve-model/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Serve a model on one node

Run from the repository root on the allocated serving node. Read the vLLM quickstart for the exact installation and foreground launch commands. This skill does not allocate a GPU or authorize a workload.

Preconditions

  • Confirm permission for the node, one isolated GPU, package installation, server startup and the validator's inference request. Record the allocation and the process you own. Never use a login shell outside that allocation or override scheduler device isolation.
  • Confirm model license, immutable revision, complete file list, reader identity, cache mount and served alias. Use manage-model-cache for missing files; do not make consumers download them.
  • Require Python 3.12 and a fresh private serving environment using examples/vllm/requirements.txt. Check wheel/driver compatibility against the quickstart; do not change drivers or the cache writer's environment.
  • Keep the whole Hub cache read-only, including blobs. Keep authentication, HF_HOME, Xet and framework caches private. Pause snapshot writes during use.

Procedure and success gate

  1. Follow quickstart steps 1–2. Require cache validator exit 0 and ok: true as the actual reader before startup. Config alone is not a complete model; name every required weight shard and tokenizer file.
  2. Use quickstart step 3 unchanged for the public example: local snapshot and tokenizer, offline loading, one GPU, foreground process, loopback only. Never enable remote model code. HF_HUB_OFFLINE=1 is not a firewall and belongs only on the loading process, not globally on clients.
  3. Wait for startup; use another shell in the same allocation and namespace to validate. This submits inference, not just a read-only health check:
python3 scripts/validation/validate_vllm.py --json \
  --base-url http://127.0.0.1:8000 --model deepops-gpt2 \
  --cache-dir /shared/hf-cache/hub \
  --repo-id openai-community/gpt2 \
  --revision 607a30d783dfa663caf39e06633721c8d4cfcd7e \
  --require-file config.json --require-file tokenizer.json --require-file model.safetensors

Read the full file on GitHub · 72 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. yesterday First seen · 72 lines · 36 tokens per session scan A 26b76d30463a

Subscribe to this mod's changes

serve-model is a skill published in the GitHub repository NVIDIA/deepops (1,485 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 36 tokens to every session and 911 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 2026-11-06.

Data and AI
Related

serve-model compared with skills from other repositories

serve-model next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
serve-modelNVIDIA/deepopsSkill1.5kyesterdayBSD-3-ClauseA36Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code