ai4science-studio: Command for Claude Code

.claude/commands/run-hydragnn.md

run-hydragnn is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (592 once invoked), scanned A, original, MIT.

A guided command for running HydraGNN, a model that makes predictions from graph-based scientific data, on AMD graphics processors in a computing cluster.

In plain words
What is it for?
Use it to load a HydraGNN checkpoint and run predictions, or to carry out smaller training jobs on an AMD cluster managed with SLURM.
Why use it?
It helps users check their cluster setup, find model files, choose inference or smaller-scale training, and provide the required settings without guessing the procedure.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is AMDResearch/ai4science-studio's own configuration. It tells Claude Code how to work on ai4science-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai4science-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AMDResearch/ai4science-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AMDResearch/ai4science-studio/main/.claude/commands/run-hydragnn.md
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 run-hydragnn

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-hydragnn/github.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/run-hydragnn)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-hydragnn"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-hydragnn/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for run-hydragnn

Your own site · 80×15
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-hydragnn"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-hydragnn.svg" alt="Reviewed on agentmods" width="80" 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 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00592
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 9d ago against content hash a8b4e4ed4258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

run-hydragnn 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 9d 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/run-hydragnn.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run HydraGNN ensemble inference on an AMD cluster

Guide the user through running HydraGNN predictive GFM inference on AMD GPUs.

Step 0 — Cluster config check

Check if .cluster-config.yaml (repo root) or ~/.config/ai4science-studio/cluster.yaml exists. If neither exists, run the /init-cluster flow first. If a config exists, read it and pre-fill container runtime and SLURM partition/account from saved values.

Step 1 — Questionnaire

Q0. Task

  • Inference — Load a checkpoint and run predictions
  • Training — Smaller-scale training (the full GFM pretraining is Frontier-scale)

Q1. (Inference) Checkpoint and config First, auto-discover: run find <paths.projects> -maxdepth 5 -name "*.pk" 2>/dev/null and find <paths.projects> -maxdepth 5 -name "config.json" 2>/dev/null (substituting paths.projects from cluster config) to check for existing checkpoints on shared storage. Present any results to the user. If nothing is found, ask:

  • Do you have a .pk checkpoint and matching config.json from the HF Hub mlupopa/HydraGNN_Predictive_GFM_2024?
  • Options: Yes, provide paths / No, download for me / Auto-discovered (use found path)

Q2. Output directory Where to write predictions? Default: <paths.projects>/hydragnn-results (read paths.projects from cluster config, never use $HOME for large outputs).


Step 2 — Download weights (if needed)

pip install huggingface-hub
huggingface-cli download mlupopa/HydraGNN_Predictive_GFM_2024 \
    --include "Ensemble_of_models/gfm_0.229/*" \
    --local-dir ./hydragnn-weights

Step 3 — Launch

Docker

cd material_science/models/HydraGNN/examples
HG_CHECKPOINT=/path/to/gfm_0.229_epoch_100.pk \
HG_CONFIG=/path/to/config.json \
./docker_run.sh inference

Manual

export HG_CHECKPOINT=/path/to/checkpoint.pk
export HG_CONFIG=/path/to/config.json
bash material_science/models/HydraGNN/examples/run_inference.sh

Read the full file on GitHub · 58 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. 9d ago First seen · 58 lines · 0 tokens per session scan A a8b4e4ed4258

Subscribe to this mod's changes

run-hydragnn 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 592 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.