Claude Code Multi-Model is a sample project that connects Anthropic’s command-line coding agent to foundation models hosted on Amazon Bedrock or self-hosted on EC2, then evaluates their coding performance. It is intended for demonstration and learning, helping users compare models for software-engineering tasks and function-generation benchmarks. The catalogue add-ons support model selection and evaluation workflows.
Borrowing it
Nothing to install: this file belongs to aws-samples/sample-claude-code-multi-model. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aws-samples/sample-claude-code-multi-model/main/.claude/skills/vllm-setup/SKILL.mdgit clone --depth 1 https://github.com/aws-samples/sample-claude-code-multi-modelWrote 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.
[](https://agentmods.dev/skills/aws-samples/sample-claude-code-multi-model/vllm-setup)<a href="https://agentmods.dev/skills/aws-samples/sample-claude-code-multi-model/vllm-setup"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-claude-code-multi-model/vllm-setup/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.
<a href="https://agentmods.dev/skills/aws-samples/sample-claude-code-multi-model/vllm-setup"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-claude-code-multi-model/vllm-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00164 | $0.02532 |
| Opus 5.5 | $0.00066 | $0.01013 |
| Sonnet 5.5 | $0.00033 | $0.00506 |
| Haiku 4.5 | $0.00016 | $0.00253 |
Grade C, and why
vllm-setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
TOKEN=$(curl -sf -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 60") Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
TOKEN=$(curl -sf -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 60") The source is not reproduced here
Licensed MIT-0
The repository is licensed MIT-0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 164 lines · 164 tokens per session scan C af3c66b80ec9
vllm-setup is a skill published in the GitHub repository aws-samples/sample-claude-code-multi-model (11 stars, last pushed 2mo ago), licensed MIT-0. It adds 164 tokens to every session and 2,532 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
demo-6-article-kg
Demo skill that web-fetches two Decoding AI knowledge-graph articles, has the agent itself distill them into a typed entity/relation graph, and renders an interactive dark-themed force-directed KG into one self-contained kg.html — no graph library, no CDN.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.