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 homelab-endpointgit 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/homelab-endpoint)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/homelab-endpoint"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/homelab-endpoint/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/homelab-endpoint"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/homelab-endpoint.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 | $0.00082 | $0.00543 |
| Opus 5 | $0.00041 | $0.00271 |
| Sonnet 5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
homelab-endpoint 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 today.
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
homelab-endpoint
Resolve a homelab service to a concrete endpoint + how to consume it. Read-only.
Source of truth for the namespace and the ${VAR} substitution convention:
docs/recipes/consuming-homelab-services.md.
The namespace (canonical values)
Host: DGX_TAILNET_HOST = dgx-llm-1.tail6d0ed4.ts.net (use anywhere on the
tailnet) · DGX_LAN_IP = 192.168.0.59 (same-LAN only).
| Service | Base URL | model / notes |
|---|---|---|
| coder-next vLLM | http://${DGX_TAILNET_HOST}:9000/v1 |
model coder-next, bearer = that stack's VLLM_API_KEY (per-stack, in its untracked .env on the DGX — not published); needs gpu-mode code |
| autoresearch vLLM | http://${DGX_TAILNET_HOST}:8003/v1 |
model autoresearch, bearer = that stack's VLLM_API_KEY (in its untracked .env on the DGX — not published); needs gpu-mode research |
| Ollama | http://${DGX_TAILNET_HOST}:11434 |
metrics exporter on :9778 |
| Observability (PromQL labels) | — | instance="homelab-1", cluster="homelab" |
Resolve
- Default to
DGX_TAILNET_HOST(works anywhere on the tailnet); useDGX_LAN_IPonly when the consumer is on the same LAN. - The two vLLM slots are mutually exclusive on the GPU — a slot is only live
when its gpu-mode is active. Check with the
gpu-modeskill before assuming:9000or:8003answers.
Report
Print the full base URL + model name + auth header (Authorization: Bearer …),
and note the gpu-mode dependency for the vLLM slots.
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.
- today Changed 5ecb578bc469
- 11d ago First seen · 36 lines · 82 tokens per session scan A 5e09b8fd8b29
homelab-endpoint is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 543 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
linkerd-patterns
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.