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 chipi/agentic-ai-homelab --skill vllm-deploygit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/vllm-deploy)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/vllm-deploy"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/vllm-deploy/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/chipi/agentic-ai-homelab/vllm-deploy"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/vllm-deploy.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 | $0.00076 | $0.00458 |
| Opus 5 | $0.00038 | $0.00229 |
| Sonnet 5 | $0.00015 | $0.00092 |
| Haiku 4.5 | $0.00008 | $0.00046 |
Grade A, and why
vllm-deploy scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`ssh dgx-llm-1 'curl -fsS http://127.0.0.1:<port>/health'` and confirm the mode What it actually says
vllm-deploy
Bring a vLLM stack up without stepping on the GPU or a broken config. Preflight is read-only; the deploy is shared-state and gated on explicit approval.
Preflight — do all of these first (read-only)
- GPU free?
ssh dgx-llm-1 '~/bin/gpu-mode-swap.sh status --json'. If a compute app holds the GPU, or the other vLLM is already up, STOP — taking the GPU is a switch, which is gated (use thegpu-modeskill and get approval). - Config valid? Run the
compose-checkskill on the stack (docker compose config -q→ PASS / ENV-MISSING / FAIL). - Env ready? If ENV-MISSING,
cp .env.example .envand fill (HF_TOKEN) before deploying.
Deploy — SHARED-STATE, explicit approval each time
Only after preflight is clean and the operator says go. The stack owns the GPU; treat the DGX as production.
- Prefer
gpu-mode-swap.sh <code|research>— it sequences the swap (brings the right stack up and the other down) rather than a bareup. - Or, run from the stack dir in place (repo-root
.envconvention):docker compose up -d. - Never
down -v, prune volumes, or restart a live stack without separate, explicit approval.
Verify
ssh dgx-llm-1 'curl -fsS http://127.0.0.1:<port>/health' and confirm the mode
matches (gpu-mode check). Report the resulting mode + health.
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.
- 9d ago First seen · 37 lines · 76 tokens per session scan A a5a84bc25645
vllm-deploy is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 458 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
holoscan-install-container
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
doca-argus
Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel /…
doca-urom-svc
Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using doca-urom: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no…