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/check-modelgit 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/check-model)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/check-model"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/check-model.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 | $0.00740 |
| Opus 5 | $0.00000 | $0.00370 |
| Sonnet 5 | $0.00000 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
check-model 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a model folder for completeness and convention compliance
Audit an existing model entry in AI4Science Studio and report any issues.
Checklist
Structure
- Folder is under the correct domain (
earth_science/,material_science/,protein_folding/,healthcare/,physics_simulation/) - Slug follows the
org__modelnaming rule, or is a public name with canonical HF id documented inREADME.md -
README.mdexists at<domain>/models/<slug>/README.md -
recipes/subfolder exists with at least one task subfolder, each containing its ownREADME.md -
examples/directory exists with at leastdocker_run.shand onerun_*.sh/run_*.py
README.md content
- Hugging Face model id present (or
N/Awith alternate weight source documented) - Task clearly described
- License (SPDX id or link) present
- Upstream code repo linked
- Paper linked (if one exists)
- If weights are not on HF: "Obtaining model weights" section with fetch snippet
examples/ scripts
-
docker_run.sh: auto-detects AMD Container Toolkit vs device passthrough; checks for existing container; auto-clones upstream repo if absent -
run_*.sh/run_*.py: key params overridable via env vars; prints config summary; exits with clear error when required inputs are missing -
preflight_<slug>.py: verifies GPU access and imports -
sbatch_*_amd.sh: uses--rocm(not--nv) for AMD/Apptainer GPU passthrough; named_amd.shnot_mi300x.sh(covers MI250X/MI300X/MI350X with rocm7.2.x) -
build_overlay_amd.sh(for HPC models with heavy pip deps): NFS staging pattern, exposesROCM_WHL_TAGas the ROCm version knob; see earth-science SKILL.md for the NFS staging pattern - All scripts are
chmod +x
Domain-specific
earth_science/: spatial/temporal resolution stated in relevant recipesmaterial_science/: input representations and unit conventions documentedprotein_folding/: license restrictions surfaced; no clinical/diagnostic implicationshealthcare/(Healthcare & Life Sciences): research/engineering-only disclaimer present; no PHI; intended use and limitations from the model card includedphysics_simulation/: physical domain stated; dataset format (HDF5, NetCDF) documented; HPC/multi-node requirements noted
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.
- 3d ago First seen · 50 lines · 0 tokens per session scan A 9c1935d07918
check-model 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 740 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:load
Load a protein target and analyze it for design.
by:set-profile
Switch model profile (quality/balanced/budget).
watch
Watch live pipeline progress for a design run.
status
Show current campaign status.
text-to-3d
Generate a static textured GLB from one subject description, locally.
scaffold-fastmcp
Scaffold a new FastMCP server with standard Life Sciences project structure following ADR-001 patterns.