What is vllm-benchmark-result-analysis?

A report generator that compares vLLM serving benchmark results before and after a code change. vLLM is software used to serve large language models, and a benchmark is a measured test of performance.

Use it to compare before-and-after vLLM serving results, generate a metrics table, and add a written summary of the most important changes.

It turns two blocks of benchmark output into percentage changes and marks metrics as improvements or regressions. This makes performance effects easier to review after an implementation change.

vllm-benchmark-result-analysis — Skill for Claude Code and Codex by sh

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, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis/github.svg)](https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis)

Your own site

<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-benchmark-result-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,066 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00123	$0.01066
Opus 5	$0.00062	$0.00533
Sonnet 5	$0.00025	$0.00213
Haiku 4.5	$0.00012	$0.00107

Measured 11d ago against content hash 4e6d89e8e5ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

vllm-benchmark-result-analysis scanned grade B 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 11d ago.

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

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

--output-dir /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/outputs \

skills/vllm-benchmark-result-analysis/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM Benchmark Summary

Workflow

Identify the input — the user pastes combined text containing a "before" block and an "after" block (or provides two separate files).
Save the input to /tmp/bench_input.txt, then run the script.
Run the script using the bundled ./scripts/compare_benchmarks.py. This generates the Performance Metrics table.
Generate the Summary — after the script runs, analyze the table data and write a narrative ## AI Summary section (see guidelines below).
Assemble and save — append the Summary to the output file, then show the complete report to the user.

Running the Script

Combined text input (most common)

Save the user's pasted text to /tmp/bench_input.txt, then:

python3 /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/scripts/compare_benchmarks.py \
    /tmp/bench_input.txt \
    --output-dir /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/outputs \
    --title "vLLM Benchmark Comparison"

Two separate files

python3 /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/scripts/compare_benchmarks.py \
    --before before.txt --after after.txt \
    --output-dir /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/outputs \
    --title "vLLM Benchmark Comparison"

Input Format

The script expects the standard vLLM benchmark output block:

Before this PR:          ← any line containing "before" (case-insensitive)

============ Serving Benchmark Result ============
Metric Name:                     value
...
==================================================

After this PR:           ← any line containing "after" (case-insensitive)

============ Serving Benchmark Result ============
...
==================================================

Metric lines must follow the pattern Metric Name: <number>. Section separator lines (===, ---) are ignored automatically.

Output

The script creates a report file under /Users/shanshan-shen/.claude/skills/vllm-benchmark-result-analysis/outputs/ containing:

Read the full file on GitHub · 99 lines

Files

What ships with it

8 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.

11d ago First seen · 99 lines · 123 tokens per session scan B 4e6d89e8e5ff

Subscribe to this mod's changes

vllm-benchmark-result-analysis 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 123 tokens to every session and 1,066 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Claude Code Data and AI agent vLLM

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.