serving-llms-vllm

A skill for deploying language-model APIs with vLLM, a server for running model inference, in production environments.

In plain words
What is it for?
Use it when serving language models through OpenAI-compatible endpoints, reducing model size with quantization, or splitting inference across multiple GPUs.
Why use it?
It helps address concerns such as response speed, request capacity, GPU memory limits, and compatibility with OpenAI-style API clients.

Skill for Claude CodeCodex

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/ariffazil/aaa/vllm
Any agent
npx skills add ariffazil/AAA --skill vllm
Clone the repo
git clone --depth 1 https://github.com/ariffazil/AAA

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00027 $0.02515
Opus 5 $0.00014 $0.01257
Sonnet 5 $0.00005 $0.00503
Haiku 4.5 $0.00003 $0.00251

Measured 3d ago against content hash ab72192b7aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

serving-llms-vllm scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:9090/metrics | grep vllm
.hermes-archived-2026-08-15/skills/mlops/inference/vllm/SKILL.md · 373 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

4 files 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.

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. 3d ago First seen · 373 lines · 27 tokens per session scan A ab72192b7aee

Subscribe to this mod's changes

serving-llms-vllm is a skill published in the GitHub repository ariffazil/AAA (2 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 27 tokens to every session and 2,515 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

hephaestus-network

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

agentlas-ai/Agentlas-OS · 75 tokens

agentlas-security-scan

Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret hephaestus security scan.

agentlas-ai/Agentlas-OS · 53 tokens

llm-runtime-architecture

Use when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compatible tools.

agentlas-ai/Agentlas-OS · 34 tokens

k8s-cost-visibility

Estimate Kubernetes infrastructure costs by querying cluster node, pod, PVC/PV, and LoadBalancer data, applying cloud pricing models, and producing cost attribution reports with storage and LoadBalancer cost tracking, grouped by namespace, workload, node, label, or annotation.

initializ/forge · 58 tokens

deploy-model

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai…

jonathan-vella/apex-accelerator · 129 tokens

model-serving-kubernetes

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and GPU resource management for production model serving.

BagelHole/DevOps-Security-Agent-Skills · 51 tokens