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.
npx agentmods add commands/amdresearch/ai4science-studio/run-mattergengit clone --depth 1 https://github.com/AMDResearch/ai4science-studioWrote 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.
[](https://agentmods.dev/commands/amdresearch/ai4science-studio/run-mattergen)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-mattergen"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-mattergen.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00987 |
| Opus 5 | $0.00000 | $0.00494 |
| Sonnet 5 | $0.00000 | $0.00197 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
run-mattergen 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run MatterGen crystal generation on an AMD cluster
Guide the user through running MatterGen end-to-end on an AMD cluster via SLURM or Docker.
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 before proceeding.
Q0. Container runtime
- Apptainer (recommended for HPC)
- Docker (simpler setup)
Q1. Task
- Inference (generate novel crystal structures)
- Training (train/fine-tune MatterGen from scratch)
Q2. (Apptainer only) SIF path
Do you have an Apptainer SIF built from rocm/pytorch:rocm7.0_ubuntu22.04_py3.10_pytorch_release_2.7.1?
- Yes — provide the full path
- No — I will generate the pull command
- Auto-discover — I will search the filesystem for existing ROCm PyTorch
.siffiles
Q3. (Inference) Generation mode
- Unconditional — generate without constraints
- Property-conditioned — specify properties and guidance factor
Q4. (Inference, conditioned) Properties
What property conditioning dict? E.g. {"chemical_system": "Li-Fe-O", "energy_above_hull": 0.0}
Q5. Partition and account How should I determine your SLURM partition and account/project?
- Provide manually — type your partition and account names
- Auto-discover — I will query SLURM to find available partitions and accounts on this cluster
Step 2 — Act on answers
Auto-discovery procedures
Run these when the user chose Auto-discover for any question. Present the results and let the user confirm or override.
SIF files (Q2):
find "$HOME" /scratch /projects /opt -maxdepth 4 -name "*.sif" 2>/dev/null | head -20
Use $HOME (not /home) so the search works when the home directory is under a non-standard prefix.
Filter results for SIF names containing rocm or pytorch. Verify with apptainer inspect <sif> if multiple candidates.
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.
- 5d ago First seen · 108 lines · 0 tokens per session scan A 953594d9d63e
run-mattergen 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 987 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.
Other commands, from other repositories
by:campaign-auto
Full autonomous campaign — research, design, screen, rank with minimal interruption.
by:load
Load a protein target and analyze it for design.
by:approve-lab
Approve lab submission to Adaptyv Bio (triple-gated).
watch
Watch live pipeline progress for a design run.
ml-project
Start a professional AI/ML research-engineer workflow for a task (any domain - CV, medical imaging, NLP/LLM, tabular, time-series). Researches papers first, picks the best method, trains/evaluates rigorously and honestly.
checklist
Generate a custom checklist for the current feature based on user requirements.