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-walrusgit 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-walrus)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-walrus"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-walrus.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 | $0.00357 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
run-walrus 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.
What it actually says
Run Walrus physics rollout on an AMD cluster
Guide the user through running Walrus autoregressive rollout 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. Input data
Do you have an input field file (.pt or .npy)? If not, the script will generate random noise as a demo.
Q1. Rollout steps How many steps? Default: 50.
Q2. Output path
Where to write the output .pt file? Default: outputs/walrus_rollout.pt.
Q3. Weights
Weights are auto-downloaded from HF (polymathic-ai/walrus) on first run. Do you have them locally already? If yes, path?
Step 2 — Launch
Docker
cd physics_simulation/models/Walrus/examples
./docker_run.sh inference
Manual
export WALRUS_STEPS=50
export WALRUS_INPUT=/path/to/input.pt # optional
python physics_simulation/models/Walrus/examples/run_inference.py
Expected results
Walrus is a standard PyTorch Transformer — runs on ROCm without modification. Weights download (~5 GB) on first run.
Output: .pt file with predicted physical field at each timestep.
Arguments
$ARGUMENTS
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 · 49 lines · 0 tokens per session scan A da96a0f9a8bf
run-walrus 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 357 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
ruview-app
Run a RuView sensing application — presence, vitals, pose, sleep, environment mapping, MAT, point cloud, or a novel RF app.
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.
checklist
Generate a custom checklist for the current feature based on user requirements.