vllm-compare-reqs

vllm-compare-reqs is a skill for Claude Code from opendatahub-io/ai-helpers. It costs 21 tokens per session (2,439 once invoked), scanned A, original, Apache-2.0.

A comparison tool for vLLM dependency files and Dockerfiles between two versions. Dependencies are the libraries a project needs, while a Dockerfile describes how to build a container image.

In plain words
What is it for?
Use it before upgrading vLLM to find new packages that need support and compare dependencies for accelerator builds such as ROCm, CUDA, TPU, or XPU.
Why use it?
It shows which runtime and build packages or source-code dependencies changed, including differences for hardware-specific builds.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md.

Part of the odh-vllm plugin — 8 skills shipped together

Good fit Use it before upgrading vLLM to find new packages that need support and compare dependencies for accelerator builds such as ROCm, CUDA, TPU, or XPU.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/ai-helpers/vllm-compare-reqs
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 opendatahub-io/ai-helpers --skill vllm-compare-reqs
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/ai-helpers

Made for: Claude Code.

Or install odh-vllm, the plugin that ships this one along with the rest of its 8 skills.

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-compare-reqs

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-compare-reqs/github.svg)](https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-compare-reqs)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-compare-reqs"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-compare-reqs/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-compare-reqs

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-compare-reqs"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-compare-reqs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00021 $0.02439
Opus 5 $0.00010 $0.01220
Sonnet 5 $0.00004 $0.00488
Haiku 4.5 $0.00002 $0.00244

Measured 8d ago against content hash 09d23cdfc224, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vllm-compare-reqs 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/compare_reqs.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.

Makes network callslowCapability

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

- **Dependencies**: Standard library only (urllib)
plugins/odh-vllm/skills/vllm-compare-reqs/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vllm Compare Requirements Skill

Purpose

Compare vllm requirements files and Dockerfiles between versions to identify dependency changes, providing intelligent analysis for AIPCC package onboarding workflows.

For accelerator builds (ROCm, CUDA, TPU, XPU), Dockerfile comparison is critical because they specify exact commits/branches for dependencies built from source (PyTorch, Triton, Flash Attention, etc.) - information not available in requirements files.

Note: Starting from v0.20, vllm moved build requirements into a build/ subdirectory (e.g., build/rocm.txt instead of rocm-build.txt). The script automatically handles both layouts, falling back to the old paths for older versions. This makes cross-version comparisons (e.g., v0.19 vs v0.20) work seamlessly.

Skill Type

Executable Script - Runs a Python script to fetch and compare requirements files from the vllm GitHub repository.

When to Use

Use this skill when you need to:

  • Compare vllm runtime AND build requirements between versions before upgrading
  • Identify new packages that need onboarding to the AIPCC wheels builder
  • Understand dependency changes for specific hardware variants (ROCm, CUDA, etc.)
  • Analyze Dockerfile ARG changes (build commits/branches for ROCm/CUDA)
  • Debug build failures related to dependency mismatches

Note: Variant comparisons include BOTH runtime and build dependencies to ensure complete coverage.

Usage

Basic Syntax

./scripts/compare_reqs.py <version1> <version2> <variant|file> [--pretty]

Arguments

  • version1: First version to compare (e.g., v0.13.0, v0.14.0rc1)
  • version2: Second version to compare
  • variant|file: Either:
    • Variant name: rocm, cuda, cpu, tpu, xpu (auto-includes runtime + build requirements + Dockerfiles)
    • Specific file: build/rocm.txt, common.txt, docker/Dockerfile.rocm, etc. (old-style paths like rocm-build.txt also accepted)
  • --pretty: Show clean categorized output (default)
  • --no-pretty: Show simple diff output

Read the full file on GitHub · 248 lines

Files

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.

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. 8d ago First seen · 248 lines · 21 tokens per session scan A 09d23cdfc224

Subscribe to this mod's changes

vllm-compare-reqs is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 2,439 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 2026-09-03.

Related

Other skills, from other repositories

github-actions-templates

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

wshobson/agents · 44 tokens

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

deepelementlab/jupyter-studio · 27 tokens

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

deepelementlab/jupyter-studio · 31 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

nft-standards

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

wshobson/agents · 48 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens