homelab-endpoint

homelab-endpoint is a skill for Claude Code, Codex from chipi/agentic-ai-homelab. It costs 82 tokens per session (543 once invoked), scanned A, original, MIT.

A read-only reference that maps named services in a home laboratory network to their endpoint URLs and calling details. A homelab is a privately operated set of computers and services.

In plain words
What is it for?
Use it when configuring a client for DGX, vLLM, Ollama, or observability services, or when someone asks for a service URL.
Why use it?
It avoids pointing an agent or client at the wrong host, port, model, or network address.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when configuring a client for DGX, vLLM, Ollama, or observability services, or when someone asks for a service URL.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chipi/agentic-ai-homelab/homelab-endpoint
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 chipi/agentic-ai-homelab --skill homelab-endpoint
Clone the repo
git clone --depth 1 https://github.com/chipi/agentic-ai-homelab

Made for: Claude Code, Codex.

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 homelab-endpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/homelab-endpoint/github.svg)](https://agentmods.dev/skills/chipi/agentic-ai-homelab/homelab-endpoint)
Your own site
<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.

agentmods 80×15 button for homelab-endpoint

Your own site · 80×15
<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>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00082 $0.00543
Opus 5 $0.00041 $0.00271
Sonnet 5 $0.00016 $0.00109
Haiku 4.5 $0.00008 $0.00054

Measured today against content hash 5ecb578bc469, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

workstation/claude/skills/homelab-endpoint/SKILL.md · 36 lines

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); use DGX_LAN_IP only 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-mode skill before assuming :9000 or :8003 answers.

Report

Print the full base URL + model name + auth header (Authorization: Bearer …), and note the gpu-mode dependency for the vLLM slots.

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. today Changed 5ecb578bc469
  2. 11d ago First seen · 36 lines · 82 tokens per session scan A 5e09b8fd8b29

Subscribe to this mod's changes

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.