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 maintainer-opsgit 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/maintainer-ops)<a href="https://agentmods.dev/skills/vllm-project/semantic-router/maintainer-ops"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/maintainer-ops/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/maintainer-ops"><img src="https://agentmods.dev/badge/skills/vllm-project/semantic-router/maintainer-ops.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 | $0.00032 | $0.00208 |
| Opus 5 | $0.00016 | $0.00104 |
| Sonnet 5 | $0.00006 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
maintainer-ops 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 yesterday.
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
Maintainer operations
Read tools/agent/docs/maintainer-ops.md and
tools/agent/maintainer-policy.yaml. Resolve the exact issue, PR, release, and
head revision before mutating GitHub. Base decisions on current main, the
actual diff, tests, CI, and related history—not on descriptions alone.
Keep discovery read-only. Store local state only under
.agent-harness/maintainer/; acquire the documented resource lease before an
apply step and release it afterward. Prefer editing a mistaken comment over
posting a duplicate. Never expose private infrastructure in public artifacts.
For PRs, put blockers first and distinguish suggestions. For issue acceptance,
use the exact /accept comment rather than applying the label directly. For a
release, verify the immutable commit and artifacts before publication.
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.
- yesterday First seen · 21 lines · 32 tokens per session scan A 693ab06998ad
maintainer-ops is a skill published in the GitHub repository vllm-project/semantic-router (5,691 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 208 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
publish-plugins
(project) Use when editing any file under skills/ or plugins/ to bump the plugin version and check the manifests.
delivery-operations
Plan safe delivery with observable rollouts, rollback criteria, and operational ownership.
docs-release-notes
Produce accurate user and operator documentation with concise, evidence-based release notes.
ferrogate-release
Use when cutting a FerroGate release — building the container image and publishing it to GHCR. Covers the standing directive to NOT use GitHub Actions (too slow) and instead gate on the local ferrogate-test suite then push locally, including the no-sudo/no-Docker host path (musl-static + crane). Use for "release"…
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.