update_vllm

update_vllm is a command for Claude Code from datathings/marketplace. It costs 0 tokens per session (1,427 once invoked), scanned A, original, Apache-2.0.

A command for updating the vLLM library, a system for serving language models, and synchronizing related skill files with its changed programming interface.

In plain words
What is it for?
Use it to inspect the current and latest stable tags, review intervening changes, update the bundled vLLM repository, and refresh the associated skills.
Why use it?
It keeps the local copy and accompanying instructions aligned with a newer stable vLLM release instead of updating them separately.

Command for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions subagents.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is cd ../../...

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 update_vllm

README.md
[![agentmods](https://agentmods.dev/badge/commands/datathings/marketplace/update_vllm.svg)](https://agentmods.dev/commands/datathings/marketplace/update_vllm)
Your own site
<a href="https://agentmods.dev/commands/datathings/marketplace/update_vllm"><img src="https://agentmods.dev/badge/commands/datathings/marketplace/update_vllm.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01427
Opus 5 $0.00000 $0.00714
Sonnet 5 $0.00000 $0.00285
Haiku 4.5 $0.00000 $0.00143

Measured 6d ago against content hash 19eac7dd8615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

update_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 6d 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.

.claude/commands/update_vllm.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update vLLM Skill to Latest Version

This command updates the vLLM library to the latest version and synchronizes all skill files with the updated API.

Working directory: plugins/vllm/

Repository Structure

plugins/vllm/
├── skills/vllm/          # Skill content (SKILL.md and references/)
├── vllm/                 # Upstream repo clone (NOT a submodule)
└── .claude-plugin/plugin.json   # Plugin manifest

The vllm/ directory is a standalone git clone from [email protected]:vllm-project/vllm.git - updated independently via git fetch and git checkout <tag>.

Process

1. Update Library to Latest Tag

cd plugins/vllm/vllm

git fetch --tags

CURRENT_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "unknown")
echo "Current tag: $CURRENT_TAG"

# Stable releases use v#.#.# format (exclude RC tags)
LATEST_TAG=$(git tag --sort=-version:refname | grep "^v" | grep -v "rc\|alpha\|beta" | head -n 1)
echo "Latest tag: $LATEST_TAG"

if [ "$CURRENT_TAG" != "unknown" ] && [ "$CURRENT_TAG" != "$LATEST_TAG" ]; then
  echo "Commits between $CURRENT_TAG and $LATEST_TAG:"
  git log --oneline "$CURRENT_TAG..$LATEST_TAG" | head -n 50

  echo -e "\nAPI-related commits:"
  git log --oneline "$CURRENT_TAG..$LATEST_TAG" --grep="API\|deprecat\|LLM\|SamplingParams\|LoRA\|multimodal" -i
fi

git checkout "$LATEST_TAG"
echo "Now on: $(git describe --tags)"

cd ../../..

2–6. Analyze API Changes & Update Documentation (subagent)

Dispatch a general-purpose subagent via the Task tool for analysis and documentation rewrite. This keeps the large source content out of the main context.

Provide the subagent with:

  • Path to source-of-truth files:
    • plugins/vllm/vllm/vllm/__init__.py — public exports
    • plugins/vllm/vllm/vllm/entrypoints/llm.pyLLM class
    • plugins/vllm/vllm/vllm/sampling_params.pySamplingParams, StructuredOutputsParams
    • plugins/vllm/vllm/vllm/outputs.py — output types
    • plugins/vllm/vllm/vllm/lora/request.pyLoRARequest
    • plugins/vllm/vllm/vllm/entrypoints/openai/ — server entrypoints and REST API
  • Path to skill references: plugins/vllm/skills/vllm/references/
  • Old tag and new tag (from Step 1 output)

Read the full file on GitHub · 125 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. 6d ago First seen · 125 lines · 0 tokens per session scan A 19eac7dd8615

Subscribe to this mod's changes

update_vllm is a command published in the GitHub repository datathings/marketplace (11 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,427 tokens. 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.