check-model

check-model is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (740 once invoked), scanned A, original, MIT.

A checklist command for reviewing model entries in AI4Science Studio, a project that documents scientific AI models and their runnable examples. It checks folders, documentation, links, scripts, and setup conventions.

In plain words
What is it for?
Use it to audit a model's README, Hugging Face reference, license, upstream links, recipes, Docker setup, and example scripts.
Why use it?
It finds missing files or information before others try to use a model. This prevents incomplete instructions and broken example runs from being discovered later.

Command for Claude Code

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 commands/amdresearch/ai4science-studio/check-model
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Claude Code.

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 check-model

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/check-model.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/check-model)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/check-model"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/check-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 $0.00000 $0.00740
Opus 5 $0.00000 $0.00370
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 3d ago against content hash 9c1935d07918, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-model 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.

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.

.claude/commands/check-model.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a model folder for completeness and convention compliance

Audit an existing model entry in AI4Science Studio and report any issues.

Checklist

Structure

  • Folder is under the correct domain (earth_science/, material_science/, protein_folding/, healthcare/, physics_simulation/)
  • Slug follows the org__model naming rule, or is a public name with canonical HF id documented in README.md
  • README.md exists at <domain>/models/<slug>/README.md
  • recipes/ subfolder exists with at least one task subfolder, each containing its own README.md
  • examples/ directory exists with at least docker_run.sh and one run_*.sh/run_*.py

README.md content

  • Hugging Face model id present (or N/A with alternate weight source documented)
  • Task clearly described
  • License (SPDX id or link) present
  • Upstream code repo linked
  • Paper linked (if one exists)
  • If weights are not on HF: "Obtaining model weights" section with fetch snippet

examples/ scripts

  • docker_run.sh: auto-detects AMD Container Toolkit vs device passthrough; checks for existing container; auto-clones upstream repo if absent
  • run_*.sh / run_*.py: key params overridable via env vars; prints config summary; exits with clear error when required inputs are missing
  • preflight_<slug>.py: verifies GPU access and imports
  • sbatch_*_amd.sh: uses --rocm (not --nv) for AMD/Apptainer GPU passthrough; named _amd.sh not _mi300x.sh (covers MI250X/MI300X/MI350X with rocm7.2.x)
  • build_overlay_amd.sh (for HPC models with heavy pip deps): NFS staging pattern, exposes ROCM_WHL_TAG as the ROCm version knob; see earth-science SKILL.md for the NFS staging pattern
  • All scripts are chmod +x

Domain-specific

  • earth_science/: spatial/temporal resolution stated in relevant recipes
  • material_science/: input representations and unit conventions documented
  • protein_folding/: license restrictions surfaced; no clinical/diagnostic implications
  • healthcare/ (Healthcare & Life Sciences): research/engineering-only disclaimer present; no PHI; intended use and limitations from the model card included
  • physics_simulation/: physical domain stated; dataset format (HDF5, NetCDF) documented; HPC/multi-node requirements noted

Read the full file on GitHub · 50 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 · 50 lines · 0 tokens per session scan A 9c1935d07918

Subscribe to this mod's changes

check-model is a command published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 740 tokens. 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.