run-llms

run-llms is a skill for Claude Code, Codex from av/harbor. It costs 114 tokens per session (10,701 once invoked), scanned F, original, Apache-2.0.

A guide to running large language models (LLMs)—AI models that generate text or code—on your own computer with Harbor. Harbor packages local AI services such as Ollama, llama.cpp, vLLM, and Open WebUI in containers managed with Docker.

In plain words
What is it for?
Use it to install Harbor, download and run local models, set up a web interface, diagnose service or GPU issues, and operate related tools such as SearXNG and Open Terminal.
Why use it?
It gives you setup and troubleshooting steps for local AI services, including checking Docker, choosing a model format, handling GPU problems, and verifying that services are running.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/av/harbor/run-llms
Any agent
npx skills add av/harbor --skill run-llms
Clone the repo
git clone --depth 1 https://github.com/av/harbor

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 run-llms

README.md
[![agentmods](https://agentmods.dev/badge/skills/av/harbor/run-llms.svg)](https://agentmods.dev/skills/av/harbor/run-llms)
Your own site
<a href="https://agentmods.dev/skills/av/harbor/run-llms"><img src="https://agentmods.dev/badge/skills/av/harbor/run-llms.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,701 The whole file, excluding the scripts and references it only reads on demand.
Security scan F 4 findings. Scan, not verified.
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 $0.00114 $0.10701
Opus 5 $0.00057 $0.05351
Sonnet 5 $0.00023 $0.02140
Haiku 4.5 $0.00011 $0.01070

Measured 4d ago against content hash b7bc007b97e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

run-llms scanned grade F with 4 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

4. Restart: sudo systemctl restart docker && harbor down && harbor up

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl https://av.codes/get-harbor.sh | bash

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf services/openterminal/data

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://av.codes/get-harbor.sh | bash
skills/run-llms/SKILL.md · 1,322 lines

How it starts

The opening of the file, as written. The whole thing — 1,322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run LLMs Locally with Harbor

Harbor is a containerized LLM toolkit. This skill enables autonomous setup, configuration, troubleshooting, and operation of local LLM infrastructure.

Agent Decision Trees

Use these decision trees to determine what action to take for common user requests.

User wants to run an LLM

1. Is Harbor installed?
   → NO: Install Harbor (see Initial Setup)
   → YES: Continue
2. Is Docker running?
   → Run: docker info
   → FAIL: Start Docker daemon, check installation
   → OK: Continue
3. Does the user have a specific model in mind?
   → YES: Determine format (Ollama tag, GGUF, HF safetensors)
     → Ollama tag (e.g. qwen3:4b): harbor pull <model> && harbor up
     → GGUF from HuggingFace: harbor pull <org/repo> && harbor up llamacpp
     → Safetensors/HF model: harbor vllm model <user/repo> && harbor up vllm
   → NO: Recommend a small default: harbor pull qwen3:4b && harbor up
4. Verify: harbor ps → confirm services healthy
5. Open UI: harbor open

User has GPU issues

1. Check NVIDIA drivers: nvidia-smi
   → FAIL: User needs to install NVIDIA drivers
   → OK: Continue
2. Check Container Toolkit: docker run --rm --gpus all nvidia/cuda:12.0-base nvidia-smi
   → FAIL: Install NVIDIA Container Toolkit, restart Docker
   → OK: Continue
3. Check service logs: harbor logs <service>  # ⚠️ TAILS INDEFINITELY! (Agents: use `docker logs harbor.<service>` instead)
   → Look for: "CUDA error", "out of memory", "no GPU"
   → OOM: See "Model won't load / OOM" troubleshooting
   → No GPU detected: Check /etc/docker/daemon.json for nvidia runtime
4. Restart: sudo systemctl restart docker && harbor down && harbor up

User wants web search in chat

1. Start SearXNG: harbor up searxng
   → SearXNG auto-wires to Open WebUI when both run together
2. If WebUI was already running: harbor restart webui
3. Verify: harbor ps | grep searxng
4. Open UI: harbor open → Web search is now available in chat

User wants to change the model

Read the full file on GitHub · 1,322 lines

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. 4d ago First seen · 1,322 lines · 114 tokens per session scan F b7bc007b97e4

Subscribe to this mod's changes

run-llms is a skill published in the GitHub repository av/harbor (3,202 stars, last pushed 4d ago), licensed Apache-2.0. It adds 114 tokens to every session and 10,701 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gws-modelarmor-sanitize-prompt

Google Model Armor: Sanitize a user prompt through a Model Armor template.

sagebynature/team-nexus · 24 tokens

knowledge-base

使用 Yuxi 知识库进行检索、打开文档、文档内定位和查看思维导图。当用户需要基于已配置知识库回答问题、核验资料或引用文档内容时使用此技能。.

xerrors/Yuxi · 54 tokens

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/claude-scientific-writer · 61 tokens

rag-knowledge

Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…

vstorm-co/full-stack-ai-agent-template · 76 tokens

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

Prismer-AI/PrismerCloud · 193 tokens

ingest

Turn external URLs and documents into LLM-ready content — load + cache web pages (HQCC compression) and OCR PDFs/images to Markdown. Use whenever the user gives a URL, asks you to read a webpage, or attaches a PDF/scan that needs to be parsed before reasoning. Executes via the cloud load, cloud search, and cloud parse…

Prismer-AI/PrismerCloud · 79 tokens