vLLM Semantic Router is a programmable routing layer that chooses or combines language models for each request in a system using multiple models and types of computing infrastructure. It helps teams route inference by signals such as user preferences, application policies, quality, cost, latency, privacy, and safety requirements. The catalogue skills and instructions support configuring and operating this model-routing system.
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.
npx skills add vllm-project/semantic-router --skill vllm-sr-agent-operationsgit clone --depth 1 https://github.com/vllm-project/semantic-routerWrote 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/vllm-project/semantic-router/vllm-sr-agent-operations)<a href="https://agentmods.dev/skills/vllm-project/semantic-router/vllm-sr-agent-operations"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/vllm-sr-agent-operations/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/vllm-project/semantic-router/vllm-sr-agent-operations"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/vllm-sr-agent-operations.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 | $0.00093 | $0.00891 |
| Opus 5 | $0.00046 | $0.00445 |
| Sonnet 5 | $0.00019 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
vllm-sr-agent-operations 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 today.
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.
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-SR agent operations
Treat the running Router as the authority for the version it supports. Use YAML as the reviewable source, the management API or CLI as transport, and immutable receipts as evidence. Do not invent a second DSL or scrape Dashboard state.
Discover before acting
- Check
GET /healthandGET /readyon the management listener. - Fetch
GET /api/v1?audience=agent&visibility=primaryfor the compact capability directory. - Narrow discovery with
?capability=<name>or fetch filtered OpenAPI from/openapi.json?capability=<name>&audience=agent. - Discover configuration progressively:
vllm-sr config schema --endpoint <management-origin>- add
--section <path>or--surface <kind:name>for one contract; - use
--fullonly when a complete schema is necessary.
The management origin normally serves /api/v1/**, /openapi.json, and
/docs. The routed inference origin separately serves OpenAI-compatible
requests such as /v1/chat/completions. Never infer one port from the other.
Use the safe control loop
For configuration changes, follow this exact order:
- Edit canonical YAML locally.
- Run local validation, then authoritative Router validation.
- Plan against current state without writing.
- Apply with the ETag returned by the plan.
- Confirm readiness and active configuration.
- Preview representative routing cases without model calls.
- Probe the Envoy-routed endpoint with real model calls and assertions.
- Run the appropriate routing workload or full model benchmark.
- Review replays, outcomes, latency, token use, cost, and failures.
- Keep the change only when its declared gate passes; otherwise apply the previous version or use config rollback.
Read configuration-loop.md when changing configuration or Recipes. Read evaluation-loop.md when testing or optimizing routing. Read deployment-loop.md for installation, serving, or model-pool changes.
What ships with it
4 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.
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.
- today First seen · 79 lines · 93 tokens per session scan A e3dce6c5deea
vllm-sr-agent-operations is a skill published in the GitHub repository vllm-project/semantic-router (5,741 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 891 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
ecs-genai
Use whenever someone runs a GPU / ML / GenAI / LLM workload on Amazon ECS: GPU on ECS, ECS GPU-optimized AMI, g4dn/g5/g6/p4/p5 on ECS, which ECS launch type for GPU, Inferentia/Trainium/Neuron on ECS, distributed training, model inference or vLLM/Triton/TGI/Ray on ECS, Capacity Blocks, GPU sharing, ASG per GPU type.…
eks-genai
Use whenever someone is building, training, fine-tuning, or serving a generative AI / LLM workload on Amazon EKS — phrased as "GPU vs Trainium/Inferentia", "vLLM on EKS", "Ray Serve / KubeRay", "distributed training on EKS", "FSx for Lustre for ML", "Karpenter for GPU", "EFA / NCCL multi-node", "DCGM / Neuron…
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.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
cli-backup-sync
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.