run-aurora

run-aurora is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (591 once invoked), scanned A, original, MIT.

A guided runner for Aurora, a weather-forecasting model that produces forecasts at 0.1-degree map resolution, on an AMD cluster.

In plain words
What is it for?
Running Aurora inference from a chosen date and time for a selected number of forecast hours using the configured Docker environment.
Why use it?
It collects the climate-data credential and forecast timing first, reducing mistakes when setting up the forecast request.

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/run-aurora
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-aurora

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-aurora.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/run-aurora)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-aurora"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-aurora.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 591 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 $0.00591
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 4d ago against content hash bd9ac16d42ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-aurora 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 4d 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-aurora.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Aurora inference on an AMD cluster

Guide the user through running Aurora (0.1° resolution) end-to-end on an AMD cluster.

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 (ask ALL questions before doing anything)

Ask the user the following questions. Do not assume any defaults. Wait for answers to all questions before proceeding.

Q0. CDS credentials Do you have a Copernicus CDS API key? If not, create a free account at cds.climate.copernicus.eu.

Q1. Forecast start date and time What date and time do you want to forecast from? (YYYYMMDD format, time defaults to 0000)

Q2. Lead time How many hours ahead do you want to forecast? (default: 24, in 6h rollout steps, max ~120 for 5 days)

Q3. Container runtime Which container runtime?

  • Docker (recommended — docker_run.sh builds and launches automatically)

Step 2 — Act on answers

Read earth_science/models/Aurora/model.yaml for full env var details.

Configure credentials

cd earth_science/models/Aurora/examples
cp env_file.template env_file
# Set CDSAPI_KEY in env_file

Launch container

bash docker_run.sh

This builds pytorchweather:latest (a PyTorch image, separate from the JAX image used by PanguWeather/GenCast) and launches an interactive container.

Run forecast (inside container)

DATE=<YYYYMMDD> LEAD_TIME=<hours> bash /examples/run_inference.sh

Step 3 — Monitor

Output is written to /predictions/aurora.grib.

# Visualize
python3 /recipe/grib_visualizer.py --input /predictions/aurora.grib

Expected results

Metric Value
Resolution 0.1° (~11 km) — highest of AMD-validated weather models
VRAM Up to 192 GB HBM3 (MI300X well-suited for 0.1° memory footprint)
Output GRIB2 with z, u, v, t, q (13 levels) + 2t, 10u, 10v, msl

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 0 tokens per session scan A bd9ac16d42ce

Subscribe to this mod's changes

run-aurora 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 591 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.