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 plugin-end-to-endgit 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/plugin-end-to-end)<a href="https://agentmods.dev/skills/vllm-project/semantic-router/plugin-end-to-end"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/plugin-end-to-end.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00410 |
| Opus 5 | $0.00032 | $0.00205 |
| Sonnet 5 | $0.00013 | $0.00082 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
plugin-end-to-end 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 8d 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.
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.
What it actually says
Plugin End to End
Trigger
- Add or change a plugin type
- Change plugin config schema, execution semantics, or plugin-exposed metadata
- Update plugin chain behavior that affects runtime or tests
Workflow
- Read change surfaces and module boundaries for plugin context
- Modify plugin config schema, execution semantics, or chain behavior
- Run
make agent-report ENV=cpu CHANGED_FILES="..."to identify impacted surfaces - Run
make agent-ci-gate CHANGED_FILES="..."to validate all constraints - Verify plugin config, runtime behavior, tests, and E2E cover the changed plugin path
Gotchas
- Plugin behavior spans config and runtime; changing one side without the other creates immediate drift.
- User-visible plugin metadata often affects headers, dashboard display, or E2E expectations even when the core hook code is small.
Must Read
- tools/agent/docs/change-surfaces.md
- tools/agent/docs/module-boundaries.md
- tools/agent/docs/testing-strategy.md
Standard Commands
make agent-report ENV=cpu CHANGED_FILES="..."make agent-ci-gate CHANGED_FILES="..."make agent-feature-gate ENV=cpu CHANGED_FILES="..."
Acceptance
- Plugin config and post-decision runtime behavior stay aligned
- Tests and E2E cover the changed plugin path
- User-visible plugin metadata is updated wherever it is displayed
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.
- 8d ago First seen · 45 lines · 63 tokens per session scan A 79010907e5ed
plugin-end-to-end is a skill published in the GitHub repository vllm-project/semantic-router (5,630 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 410 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
vllm-test-generator
A test-writing guide for vLLM, an open-source system for running large language models. It helps create unit, integration, and end-to-end tests that match the project’s existing style.
ui-harness-cli
Run the Agentweaver persona-driven Playwright UI evidence harness. Use for a specific persona's deployed browser flow, end-to-end UI validation, or investigation of a UI-reported issue.
api-harness
Use the API harness to drive Agentweaver through its REST API, capture the complete request/response evidence, and emit a normalized agentweaver.persona-judge-verdict/v1 JSON verdict. It is for backend/API end-to-end validation; use the UI or MCP harness for those surfaces.
persona-briefs
Use this contract when you need to discover the current built-in scenario/persona catalog for one harness surface, or generate a reviewed new persona core and surface adapter for a new test intent.
ferrogate-test
Use when working in the FerroGate repo and the task involves the ferrogate-test Rust CLI itself — running Admin API or gateway API E2E coverage, CI harness verification, Docker-backed cluster scenarios, editing tools/ferrogate-test, or release-grade end-to-end validation. For deciding which test layer a change needs…
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.