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-semlaflowgit 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-semlaflow)<a href="https://agentmods.dev/commands/amdresearch/ai4science-studio/run-semlaflow"><img src="https://agentmods.dev/badge/commands/amdresearch/ai4science-studio/run-semlaflow.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 | $0.00431 |
| Opus 5 | $0.00000 | $0.00216 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
run-semlaflow 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 SemlaFlow 3D molecular generation on an AMD cluster
Guide the user through generating 3D molecular structures with SemlaFlow on AMD GPUs.
Research / engineering use only. Not for clinical or diagnostic use.
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. Checkpoint path
Do you have a pretrained SemlaFlow .ckpt file? (Download from Google Drive links in the upstream repo)
Q1. Dataset
- drugs (GEOM-Drugs, ~450k drug-like conformers)
- qm9 (QM9, ~134k small organic molecules)
Q2. torch.compile Enable torch.compile for ~44% speedup? (Recommended: yes)
Q3. Output path Where to write the generated SDF file?
Step 2 — Launch
Docker
cd healthcare/models/SemlaFlow/examples
CHECKPOINT=<path> DATASET=<qm9|drugs> ./docker_run.sh inference
Manual
export CHECKPOINT=<path>
export DATASET=<qm9|drugs>
export USE_COMPILE=1
export NO_EMA=1
bash healthcare/models/SemlaFlow/examples/run_inference.sh
Expected results
| Configuration | Notes |
|---|---|
| drugs + compile + no_ema | Fastest; ~44% speedup from compile, ~8% from no_ema |
| qm9 + compile + no_ema | Smaller molecules, faster per batch |
Output: SDF file with generated 3D molecular structures.
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 · 57 lines · 0 tokens per session scan A fd3b9226771d
run-semlaflow 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 431 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
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.
by:load
Load a protein target and analyze it for design.
by:approve-lab
Approve lab submission to Adaptyv Bio (triple-gated).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.