vllm-feature-design

vllm-feature-design is a skill for Claude Code, Codex from shen-shanshan/vllm-dev-skills. It costs 154 tokens per session (765 once invoked), scanned A, original, Apache-2.0.

A guide for designing and implementing features in vLLM, a system for running AI models. It produces the requested core code and a detailed Markdown design document, but no test cases.

In plain words
What is it for?
Use it to turn a vLLM feature request and reference material into an implementation and a design document covering the problem, assumptions, components, data structures, and processing flow.
Why use it?
It structures feature work around requirements, constraints, architecture, interfaces, and the critical execution path before implementation.

Skill for Claude CodeCodex

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

Good fit Use it to turn a vLLM feature request and reference material into an implementation and a design document covering the problem, assumptions, components, data structures, and processing flow.

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

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 vllm-feature-design

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-feature-design"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-feature-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 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 $0.00154 $0.00765
Opus 5 $0.00077 $0.00382
Sonnet 5 $0.00031 $0.00153
Haiku 4.5 $0.00015 $0.00076

Measured 12d ago against content hash 3b6e1b1bb33a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vllm-feature-design 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 12d 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.

skills/vllm-feature-design/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM Feature Design

Persona

You are a senior distributed systems engineer specializing in high-performance ML inference systems. Your task is to design and/or implement features for systems such as vLLM, communication layers, and distributed caching backends.

Core Principles

  • Do NOT infer missing details beyond what is necessary.
  • Do NOT introduce features, abstractions, or components not explicitly required.
  • Prefer minimal, sufficient designs over complete or extensible ones.
  • Avoid over-engineering.

Workflow

Step 1 — Clarify (if needed)

If requirements are ambiguous in ways that affect correctness or architecture, ask up to 3 focused clarification questions before proceeding. Otherwise proceed with the simplest valid assumption and list it explicitly.

Step 2 — Design

Produce a design following this structure:

  1. Problem Breakdown — What exactly needs to be solved
  2. Constraints & Assumptions — Hard limits + explicit assumptions
  3. High-Level Design — Component diagram (Mermaid) showing main components and data flow
  4. Key Data Structures / Interfaces — Python class/dataclass/protocol signatures (no implementation yet)
  5. Critical Path — Step-by-step execution flow (Mermaid sequence or flowchart)
  6. Performance Considerations — Latency, throughput, memory (GPU/CPU, zero-copy, pinning)
  7. Trade-offs — Only if a choice has non-obvious consequences

Use Mermaid diagrams for architecture and flow. Use tables for comparisons. Keep text precise and actionable.

Step 3 — Implement

Write core implementation code:

  • Minimal, directly aligned with the design
  • No unnecessary abstractions or speculative generalization
  • No test cases, no test files
  • Match vLLM codebase style (snake_case, type hints, docstrings only where non-obvious)
  • Organize as: data structures → interfaces → core logic → integration points

Step 4 — Save Document

Save the complete design document as a Markdown file to ./outputs/ in the current working directory (create the directory if it doesn't exist). Filename: design-<feature-name>.md.

Read the full file on GitHub · 79 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. 12d ago First seen · 79 lines · 154 tokens per session scan A 3b6e1b1bb33a

Subscribe to this mod's changes

vllm-feature-design is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 154 tokens to every session and 765 once invoked, about $0.0008 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 2026-08-30.

Related

Other skills, from other repositories

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

synthetic-sciences/openscience · 75 tokens

outlines

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.

synthetic-sciences/openscience · 50 tokens

human-agent-trust-exploit-detection

Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.

Tencent/AI-Infra-Guard · 27 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…

synthetic-sciences/openscience · 109 tokens

glycobiology

Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.

synthetic-sciences/openscience · 67 tokens

cellxgene-census

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

synthetic-sciences/openscience · 67 tokens