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-orbit2git 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-orbit2)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-orbit2"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-orbit2.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 | $0.00000 | $0.02131 |
| Opus 5 | $0.00000 | $0.01066 |
| Sonnet 5 | $0.00000 | $0.00426 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
run-orbit2 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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run ORBIT-2 inference/visualization on an AMD cluster
Guide the user through running ORBIT-2 end-to-end 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,
srun --mpi=pmixfor multi-GPU,--rocmflag) - Docker (simpler setup, no overlay needed, uses
torchrunfor multi-GPU instead ofsrun, single-node only)
Q1. Upstream repo Do you have the ORBIT-2 upstream code cloned locally?
- Yes — provide the full path (
ORBIT2_ROOT) - No — I will generate the clone command
- Auto-discover — I will search the filesystem for an existing ORBIT-2 clone
Q2. (Apptainer only) SIF path
Do you have an Apptainer SIF built from rocm/pytorch:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0?
- 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. (Apptainer only) Overlay
Do you have a pre-built ORBIT-2 overlay image (orbit2-overlay.img)?
- Yes — provide the full path
- No, build one — one-time ~15 min job that skips dep install on every future run
- No, skip overlay — pay the ~15 min install cost per job
- Auto-discover — I will search the filesystem for an existing overlay image
Q4. Data mode Which data mode do you want to use?
- Synthetic — generates a small ~2 MB dataset automatically, downloads the smallest checkpoint from HuggingFace. No real data needed. Use this for a smoke-test.
- Real data — requires ERA5/PRISM data staged on the cluster. You will need to provide the config YAML path and checkpoint path.
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.
- 4d ago First seen · 176 lines · 0 tokens per session scan A 02003e87d781
run-orbit2 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 2,131 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:welcome
First-run orientation -- what BY can do and where to start.
screen
Run full screening battery on a design.
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.