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 openclaw-vsr-bridgegit 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/openclaw-vsr-bridge)<a href="https://agentmods.dev/skills/vllm-project/semantic-router/openclaw-vsr-bridge"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/openclaw-vsr-bridge/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/openclaw-vsr-bridge"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/openclaw-vsr-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 27 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00042 | $0.00567 |
| Opus 5 | $0.00021 | $0.00283 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade C, and why
openclaw-vsr-bridge 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 11d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://vllm-sr.ai/install.sh | bash -s -- --mode cli --runtime skip --no-launch Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` What it actually says
OpenClaw VSR Bridge
When To Use
- Use this skill when an OpenClaw agent should install VSR without auto-launching the dashboard.
- Use this skill when an existing
openclaw.jsonshould be moved under VSR management. - Use this skill when you want the OpenClaw model base URL rewritten only after canonical
config.yamlis written successfully.
Requirements
curlbash- write access to the OpenClaw config path and the target VSR config path
Workflow
-
Check whether VSR is already installed with
command -v vllm-sr. -
If VSR is missing, run the supported installer in agent-safe mode:
curl -fsSL https://vllm-sr.ai/install.sh | bash -s -- --mode cli --runtime skip --no-launch -
Locate the OpenClaw config in this order unless the user already gave you a path:
$OPENCLAW_CONFIG_PATH./openclaw.json~/.openclaw/openclaw.json
-
Import the OpenClaw model providers into canonical VSR config:
vllm-sr config import --from openclaw --source <openclaw.json> --target config.yaml -
Do not pass
--forceunless the user explicitly approves overwriting existing backup files. -
After a successful import, report:
- the imported logical model names
- the canonical target config path
- the rewritten OpenClaw config path
- the rewritten OpenClaw base URL
- the backup file paths, if any
-
Suggest the next validation commands:
vllm-sr validate --config config.yaml vllm-sr config router --config config.yaml -
If the user wants runtime verification after validation, suggest:
vllm-sr serve --config config.yaml curl http://127.0.0.1:8899/v1/models
Boundaries
- Do not invent a second installer path. Use the supported installer above.
- Do not rewrite OpenClaw before the VSR target config has been written successfully.
- Do not import OpenClaw rooms, teams, browser settings, command settings, or memory history into VSR.
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 · 66 lines · 42 tokens per session scan C a5bacd088fa5
openclaw-vsr-bridge is a skill published in the GitHub repository vllm-project/semantic-router (5,717 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 567 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
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.
cli-resilience
Inspect and manage circuit-breaker states, connection cooldowns, quota limits, and backoff levels from the CLI. Reset stuck providers and configure resilience thresholds.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.