vllm

vllm is a skill for Claude Code, Codex from magnus919/agent-skills. It costs 196 tokens per session (3,875 once invoked), scanned A, original, MIT.

A guide for running vLLM, a server that provides access to AI language models through an API. It covers deployment, model and GPU settings, request batching, performance measurement, and operational changes.

In plain words
What is it for?
Use it to deploy vLLM with Docker or Kubernetes, configure quantization and GPU parallelism, expose an OpenAI-compatible API, benchmark requests, and tune or troubleshoot the server.
Why use it?
It brings the many configuration and maintenance tasks of serving a model together, including checking performance and safely upgrading or rolling back.

Skill for Claude CodeCodex

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

Good fit Use it to deploy vLLM with Docker or Kubernetes, configure quantization and GPU parallelism, expose an OpenAI-compatible API, benchmark requests, and tune or troubleshoot the server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magnus919/agent-skills/vllm
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 magnus919/agent-skills --skill vllm
Clone the repo
git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin vllm/plugin install vllm after adding the marketplace above.

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 vllm

README.md
[![agentmods](https://agentmods.dev/badge/skills/magnus919/agent-skills/vllm/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/vllm)
Your own site
<a href="https://agentmods.dev/skills/magnus919/agent-skills/vllm"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/vllm/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 vllm

Your own site · 80×15
<a href="https://agentmods.dev/skills/magnus919/agent-skills/vllm"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/vllm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,875 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 63
    Potential security issue detected. Manual review is recommended.
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium Excessive Agency · line 35
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00196 $0.03875
Opus 5 $0.00098 $0.01937
Sonnet 5 $0.00039 $0.00775
Haiku 4.5 $0.00020 $0.00387

Measured 7d ago against content hash a90c5f21dc2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vllm 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test_vllm_health.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

vllm/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM Inference Serving

Use this skill to operate vLLM as a production inference server: deploy it with Docker or Kubernetes, configure the model and engine (quantization, tensor parallelism, KV cache, context length), serve the OpenAI-compatible API surface, benchmark throughput and latency with comparable evidence, tune continuous batching, operate the GPUs underneath, and upgrade or roll back safely. This is a tool skill for one named engine. Serving methodology — engine selection, quantization trade-offs, deployment plans, regression triage — belongs to ml-engineering; local single-node GGUF serving with the llama.cpp stack belongs to llama-cpp. This skill owns the day-to-day operation of vLLM itself.

Operating contract

  1. Record the deployment before tuning it. Capture the vLLM version or image digest, model and revision, quantization, parallelism, max-model-len, KV cache settings, batching limits, GPU inventory, and workload. The serving config template exists for exactly this.
  2. Confirm the target, scope, and rollback path before acting. Read-only discovery (health probes, /metrics, nvidia-smi) may proceed without confirmation. Mutations — restarting a server, changing serving args, scaling replicas, upgrading the image — require an explicit human directive naming the deployment.
  3. A server that responds is not a server that serves. /health returning 200 proves liveness, not that the model loaded or that inference works. Verify at the delivery boundary: /v1/models reports the served model and a representative request returns generated tokens.
  4. Benchmark before and after every change. vLLM flags, defaults, and behavior change between releases; an unmeasured tuning change is a guess. Compare only matched conditions (version, model, GPU, context, batch, workload) and record the evidence in the benchmark run record.
  5. Keep evidence bounded. Summarize logs, configs, and metrics; never dump full server logs, .env files, or HF tokens into chat. --enable-log-requests with debug logging can leak prompt content; keep request logging off or redacted in shared sessions.

Read the full file on GitHub · 153 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. 7d ago First seen · 153 lines · 196 tokens per session scan A a90c5f21dc2b

Subscribe to this mod's changes

vllm is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 196 tokens to every session and 3,875 once invoked, about $0.0010 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 2026-09-05.