hosted-model-ctl

hosted-model-ctl is a skill for Claude Code, Codex from rhtevan/agentfs. It costs 48 tokens per session (1,872 once invoked), scanned A, original, Apache-2.0.

A skill for deploying and testing self-hosted language-model containers on NVIDIA GPUs using Podman, a tool for running containers. It uses predefined profiles checked against available GPU memory.

In plain words
What is it for?
Use it to start, manage, and test selected local language-model deployments across configured GPU hosts. The available profiles cover different models, engines, context sizes, and hardware setups.
Why use it?
It avoids choosing incompatible model and hardware combinations manually. Only one profile runs on a host at a time, so changing profiles replaces the current deployment.

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/rhtevan/agentfs/hosted-model-ctl
Any agent
npx skills add rhtevan/agentfs --skill hosted-model-ctl
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

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 hosted-model-ctl

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhtevan/agentfs/hosted-model-ctl.svg)](https://agentmods.dev/skills/rhtevan/agentfs/hosted-model-ctl)
Your own site
<a href="https://agentmods.dev/skills/rhtevan/agentfs/hosted-model-ctl"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/hosted-model-ctl.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,872 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00048 $0.01872
Opus 5 $0.00024 $0.00936
Sonnet 5 $0.00010 $0.00374
Haiku 4.5 $0.00005 $0.00187

Measured 3d ago against content hash 661d4b111284, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hosted-model-ctl 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 3d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/common.sh, scripts/list.sh, scripts/pre-check.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hosted-model-ctl/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hosted Model Control

Deploy, manage, and test self-hosted LLM model containers on NVIDIA GPUs via Podman. All deployments use profiles — curated, VRAM-validated configurations. No individual model aliases.

Hardware

Host SSH GPUs VRAM Bandwidth Port
rhtevan-work rhtevan-work 1× RTX A500 4 GB 128 GB/s 10000
rhel-ai rhel-ai 4× NVIDIA L4 88 GB 1,200 GB/s 9000

Deployment Profiles

One profile active per host at a time (mutual exclusion). All profiles on the same host share a port — deploying a new profile automatically stops the current one.

Full details in references/deployment-profiles.md.

rhtevan-work (port 10000)

Profile Model Engine Context Speed Default
g3b-16k Granite 3B Q4_K_M llama.cpp 16K 37 tok/s
g350m-2k Granite 4.0 350M FP16 vLLM 2K 44 tok/s

rhel-ai (port 9000)

Profile Model Engine TP Context Speed Default
g8b-fp8-spec-128k Granite 8B FP8 + 3B FP8 draft vLLM spec 4 128K 58-79 tok/s
g8b-spec-128k Granite 8B BF16 + 3B BF16 draft vLLM spec 4 128K 19-25 tok/s

Speculative Decoding

The g8b-spec-* profiles use draft model speculation: a Granite 3B model generates candidate tokens, then the 8B target verifies them in a single forward pass — converting wasted GPU compute into useful token verification (2-6× speedup).

  • g8b-fp8-spec-128k: FP8 weights + CUDA graphs (recommended, ~70 tok/s)
  • g8b-spec-128k: BF16 weights + --enforce-eager (safe fallback, ~20 tok/s)

Specification

ID Capability Verifiable By
S1 List all profiles with container status scripts/list.sh → table output
S2 Pre-check host readiness scripts/pre-check.sh HOST → pass/fail report
S3 Deploy profile (idempotent) scripts/setup.sh PROFILE → container created, API HTTP 200
S4 Start existing profile (mutual exclusion) scripts/start.sh PROFILE → running
S5a Stop profile scripts/stop.sh PROFILE → stopped, state cleared
S5b Stop all containers across both hosts scripts/stop.sh all → all exited
S6 Show status (includes active profile) scripts/status.sh [PROFILE] → status report
S7 Test running model scripts/test.sh PROFILE → 4 tests pass
S8 Generate platform report scripts/report.sh [HOST] → markdown report

Read the full file on GitHub · 184 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. 3d ago First seen · 184 lines · 48 tokens per session scan A 661d4b111284

Subscribe to this mod's changes

hosted-model-ctl is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,872 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 2026-08-31.

Related

Other skills, from other repositories

harbor

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…

av/harbor · 114 tokens

airunway-aks-setup

Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on…

microsoft/azure-skills · 121 tokens

rag-blueprint

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion…

NVIDIA-AI-Blueprints/rag · 92 tokens

huggingface-spaces

Build, deploy, debug, or maintain a Hugging Face Space using Gradio, Docker, or Static SDKs. Use for general Space hosting and configuration; use huggingface-zerogpu for ZeroGPU runtime constraints and lora-space-builder for LoRA demos.

waybarrios/opencode-power-pack · 60 tokens

tao-run-automl

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation…

NVIDIA-TAO/tao-skill-bank · 235 tokens

nvwb

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI. This skill should be used when the user wants to create, clone, build, manage, or configure AI Workbench projects, contexts, or environments.

brevdev/workshop-build-an-agent · 52 tokens