ai4science-studio: Command for Claude Code

.claude/commands/run-gpmolformer.md

run-gpmolformer is a command for Claude Code from AMDResearch/ai4science-studio. It costs 0 tokens per session (1,820 once invoked), scanned A, original, MIT.

A guided runner for GP-MoLFormer, a model that generates molecular structures represented as SMILES strings, on an AMD cluster using SLURM.

In plain words
What is it for?
Generating novel molecule strings with Apptainer or Docker on AMD GPUs and running the configured job through the cluster scheduler.
Why use it?
It checks the cluster and container choices before launching a research run, while clearly limiting the output to non-clinical drug-discovery research.

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-gpmolformer.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-gpmolformer

README.md
[![agentmods](https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-gpmolformer.svg)](https://agentmods.dev/commands/amdresearch/ai4science-studio/run-gpmolformer)
Your own site
<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-gpmolformer"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-gpmolformer.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 1,820 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 $0.01820
Opus 5 $0.00000 $0.00910
Sonnet 5 $0.00000 $0.00364
Haiku 4.5 $0.00000 $0.00182

Measured 7d ago against content hash a88d1423bd31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

run-gpmolformer 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 7d 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-gpmolformer.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run GP-MoLFormer molecule generation on an AMD cluster

Research / engineering use only. Outputs are novel SMILES strings for drug-discovery research. Not validated for clinical or therapeutic use.

Guide the user through running GP-MoLFormer on an AMD cluster via SLURM.

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. Container runtime Which container runtime do you want to use?

  • Apptainer (recommended for HPC — supports overlays, --rocm flag for GPU)
  • Docker (simpler setup, no overlay needed, but no MPI support and env vars must be appended not replaced)

Q1. (Apptainer only) SIF path Do you have an Apptainer SIF to use? The recommended image is rocm/pytorch:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0 (py3.12) — it has validated GPU detection on MI300A clusters with current amdgpu drivers. The older rocm7.0 py3.10 image works on MI300X but silently falls back to CPU on MI300A clusters with newer drivers.

  • Yes — provide the full path
  • No — I will generate the pull command
  • Auto-discover — I will search the filesystem for existing ROCm PyTorch .sif files

Q2. Work directory Where do you want the GP-MoLFormer repo clone, model weights, and output CSV to live on the host? (full path — this directory is reused across runs so the clone is not re-downloaded each time)

Q3. Generation mode Which generation mode do you want?

  • Unconditional — generates molecules freely with no structural constraint.
  • Scaffold-constrained — completes molecules around a SMILES fragment you provide (e.g. c1ccccc1 for a benzene ring).

Read the full file on GitHub · 140 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. 7d ago First seen · 140 lines · 0 tokens per session scan A a88d1423bd31

Subscribe to this mod's changes

run-gpmolformer 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 1,820 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.