A tool for finding and resolving Hugging Face machine-learning models to a local path before they are run. It supports GGUF, MLX, and safetensors model files.

Use it when loading or running a local language model with tools such as llama.cpp, Ollama, MLX, vLLM, or Transformers.

It prevents local model workflows from downloading models through the wrong method or using an invented model identifier. It can search when the model request is described loosely.

resolve — Skill for Claude Code by alexziskind1: A tool for finding and resolving Hugging Face machine-learning…

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/alexziskind1/model-shelf/resolve

Any agent

npx skills add alexziskind1/model-shelf --skill resolve

Clone the repo

git clone --depth 1 https://github.com/alexziskind1/model-shelf

Made for: Claude Code.

Or install model-shelf, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alexziskind1/model-shelf/resolve.svg)](https://agentmods.dev/skills/alexziskind1/model-shelf/resolve)

Your own site

<a href="https://agentmods.dev/skills/alexziskind1/model-shelf/resolve"><img src="https://agentmods.dev/badge/skills/alexziskind1/model-shelf/resolve.svg" alt="Measured on agentmods" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 922 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.00922
Opus 5	$0.00033	$0.00461
Sonnet 5	$0.00013	$0.00184
Haiku 4.5	$0.00007	$0.00092

Measured 6d ago against content hash 1ed441ddb125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

resolve 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 6d 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.

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/resolve/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve a Hugging Face model locally

When the user wants to load, run, or use a Hugging Face model — always go through model-shelf. Do not invoke huggingface-cli download, hf download, snapshot_download, or any other direct download command.

The user does not need to give you an exact org/repo id. Loose descriptions ("qwen 3 4b mlx 4-bit", "the latest llama 3.1") are normal and expected. Do not push back on whether a model exists — your training data is stale and Model Shelf can search the live Hub.

Workflow

Decide whether to search first.
- If the user gave a clean org/repo string (e.g. Qwen/Qwen3-14B-GGUF), skip to step 2.
- Otherwise the input is loose — run:
```
model-shelf find "<user's words>" [--format gguf|mlx|safetensors] --json --limit 5
```
  Use any format hint from the user (mlx, gguf, safetensors). Pick the top result that matches the user's format/quant intent. Use its repo_id as the input to step 2. If find returns nothing, tell the user no matching model was found — do not invent a repo id.
Resolve the repo to a local path.
```
model-shelf resolve <repo_id> [--format gguf|mlx|safetensors] [--quant <QUANT>] --json
```
- --format is auto-detected from repo_id if omitted:
  - *-GGUF (case-insensitive) → gguf
  - mlx-community/* or *-mlx → mlx
  - everything else → safetensors
- --quant is required for gguf (e.g. Q4_K_M); ignored otherwise.
Use the returned path with the user's runtime:
- gguf: file path → llama.cpp / llama-server / Ollama / LM Studio
- mlx: directory path → mlx_lm.generate / mlx_lm.server (Apple Silicon)
- safetensors: directory path → transformers / vllm
Error handling:
- If status == "missing", downloads are disabled in their config — surface that to the user and stop.
- If model-shelf exits non-zero with a message on stderr, surface the error verbatim and stop. Do not work around it — don't fall back to huggingface-cli, don't change paths, don't retry. Common causes:
  - Volume not mounted — user's external drive isn't connected.
  - Shelf not initialized — error tells them to run model-shelf init. Don't run it for them unless they explicitly ask; the curated shelf is a deliberate one-time setup the user owns.

Read the full file on GitHub · 73 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.

6d ago First seen · 73 lines · 66 tokens per session scan A 1ed441ddb125

Subscribe to this mod's changes

resolve is a skill published in the GitHub repository alexziskind1/model-shelf (129 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 922 once invoked, about $0.0003 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 2026-08-30.

Data and AI

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens