openclaw-vsr-bridge

openclaw-vsr-bridge is a skill for Claude Code from vllm-project/semantic-router. It costs 42 tokens per session (567 once invoked), scanned C, original, Apache-2.0.

A setup procedure that connects OpenClaw, an agent platform, to vLLM Semantic Router, a service that chooses and routes model requests. It imports model providers into the router’s configuration before changing OpenClaw’s endpoint.

In plain words
What is it for?
It helps install the router in command-line mode, find the OpenClaw configuration, import its providers, and update OpenClaw after a successful import.
Why use it?
It reduces the risk of switching OpenClaw to an incomplete or incorrectly configured model router.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Good fit It helps install the router in command-line mode, find the OpenClaw configuration, import its providers, and update OpenClaw after a successful import.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vllm-project/semantic-router/openclaw-vsr-bridge
About the project

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.

vllm-project/semantic-router · 5,717 stars · on GitHub · vllm-sr.ai

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 vllm-project/semantic-router --skill openclaw-vsr-bridge
Clone the repo
git clone --depth 1 https://github.com/vllm-project/semantic-router

Made for: Claude Code.

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 openclaw-vsr-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/vllm-project/semantic-router/openclaw-vsr-bridge/github.svg)](https://agentmods.dev/skills/vllm-project/semantic-router/openclaw-vsr-bridge)
Your own site
<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.

agentmods 80×15 button for openclaw-vsr-bridge

Your own site · 80×15
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
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 $0.00042 $0.00567
Opus 5 $0.00021 $0.00283
Sonnet 5 $0.00008 $0.00113
Haiku 4.5 $0.00004 $0.00057

Measured 11d ago against content hash a5bacd088fa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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`
dashboard/backend/skillpacks/openclaw-vsr-bridge/SKILL.md · 66 lines

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.json should be moved under VSR management.
  • Use this skill when you want the OpenClaw model base URL rewritten only after canonical config.yaml is written successfully.

Requirements

  • curl
  • bash
  • write access to the OpenClaw config path and the target VSR config path

Workflow

  1. Check whether VSR is already installed with command -v vllm-sr.

  2. 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
    
  3. Locate the OpenClaw config in this order unless the user already gave you a path:

    • $OPENCLAW_CONFIG_PATH
    • ./openclaw.json
    • ~/.openclaw/openclaw.json
  4. Import the OpenClaw model providers into canonical VSR config:

    vllm-sr config import --from openclaw --source <openclaw.json> --target config.yaml
    
  5. Do not pass --force unless the user explicitly approves overwriting existing backup files.

  6. 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
  7. Suggest the next validation commands:

    vllm-sr validate --config config.yaml
    vllm-sr config router --config config.yaml
    
  8. 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.
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. 11d ago First seen · 66 lines · 42 tokens per session scan C a5bacd088fa5

Subscribe to this mod's changes

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.