model-hub

model-hub is a skill for Claude Code, Codex from qualcomm/qai-appbuilder. It costs 80 tokens per session (3,759 once invoked), scanned A, original, no licence file.

A model download and deployment guide for Qualcomm AI Hub, a service that provides pre-exported machine-learning models. It can prepare downloaded .bin, .dlc, or ONNX packages for import into App Builder and run them on a device.

In plain words
What is it for?
Use it to download an AI Hub model, test inference on a device, and export it as an App Builder-ready Pack.
Why use it?
It avoids custom model conversion when a suitable prebuilt package already exists. It also gives a path from the downloaded model to a package that App Builder can use.

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/qualcomm/qai-appbuilder/model-hub
Any agent
npx skills add qualcomm/qai-appbuilder --skill model-hub
Clone the repo
git clone --depth 1 https://github.com/qualcomm/qai-appbuilder

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 model-hub

README.md
[![agentmods](https://agentmods.dev/badge/skills/qualcomm/qai-appbuilder/model-hub.svg)](https://agentmods.dev/skills/qualcomm/qai-appbuilder/model-hub)
Your own site
<a href="https://agentmods.dev/skills/qualcomm/qai-appbuilder/model-hub"><img src="https://agentmods.dev/badge/skills/qualcomm/qai-appbuilder/model-hub.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,759 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00080 $0.03759
Opus 5 $0.00040 $0.01879
Sonnet 5 $0.00016 $0.00752
Haiku 4.5 $0.00008 $0.00376

Measured 6d ago against content hash 98e37318cdf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

model-hub 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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (models/beit/infer_beit.py, models/melotts_zh/infer_melotts_zh.py, models/zipformer/infer_zipformer.py, …), 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.

Makes network callslowCapability

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

exec('curl -k -L "<url>" -o "C:/WoS_AI/<model>/<file>.zip" --create-dirs', timeout=300)
tools/qaiappbuilder/factory/chat_features/model-hub/SKILL.md · 246 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 6d ago First seen · 246 lines · 80 tokens per session scan A 98e37318cdf4

Subscribe to this mod's changes

model-hub is a skill published in the GitHub repository qualcomm/qai-appbuilder (202 stars, last pushed 2d ago), with no licence file. It adds 80 tokens to every session and 3,759 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 2026-08-30.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens