A workflow for submitting materials-science or machine-learning jobs to Rockie GPU computing capacity. It selects resources and prepares the job script from a description such as a quantum calculation, molecular simulation, training run, or inference batch.

Use it to run GPU-bound DFT, molecular-dynamics, training, fine-tuning, inference, or similar experiments on Rockie.

It handles the translation from a natural-language compute request to a submitted and monitored GPU job, while keeping local-only work off the paid compute path.

experiment — Skill for Claude Code and Codex by Rockielab/rockie-codex

Install

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.

Any agent

npx skills add Rockielab/rockie-codex --skill experiment

Clone the repo

git clone --depth 1 https://github.com/Rockielab/rockie-codex

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rockielab/rockie-codex/experiment/github.svg)](https://agentmods.dev/skills/rockielab/rockie-codex/experiment)

Your own site

<a href="https://agentmods.dev/skills/rockielab/rockie-codex/experiment"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/experiment/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rockielab/rockie-codex/experiment"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,597 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00131	$0.02597
Opus 5.5	$0.00052	$0.01039
Sonnet 5.5	$0.00026	$0.00519
Haiku 4.5	$0.00013	$0.00260

Measured 1mo ago against content hash 5b719c528cc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

experiment scanned grade A with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 11 executable files (runtime/monitor_contract.py, runtime/monitoring_profiles.py, runtime/submit.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

JSON artifact to `runtime/submit.py` (don't shell out to curl directly —

project-extension/agents/skills/experiment/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

experiment — submit a GPU job

Wraps the Phase 5 job runner. The agent decides the GPU shape, writes the script, hands it to platform-context, and tails the run.

When to invoke

User asks to "run an experiment", "submit a job", "kick off a calculation", "train this model".
User describes a calculation that obviously needs a GPU (DFT, AIMD, large-scale MD with PME, model fine-tuning, inference batch).
User asks to use the experiment skill directly.

If the task is local-only (pre-processing, data wrangling, plotting), do NOT use the experiment skill — run it inline. The skill is for GPU-bound work that the user is willing to pay GPU credit for.

First-experiment GPU-mode disclosure

Before submitting the user's FIRST experiment in a workspace (i.e. neither .codex/gpu-custom.md exists nor $ROCKIE_GPU_MODE is set), the agent emits one neutral sentence before proceeding:

Your options are Rockie GPU (Rockie provisions the pod and the per-hour price it quotes already includes everything) or your own hardware (ROCKIE_GPU_MODE=custom then ask Codex to run gpu-custom-setup). Default is Rockie GPU — proceeding with that unless you say otherwise.

That's the entire disclosure. Do NOT:

repeat it on subsequent experiments
pitch Rockie GPU with adjectives like "easy" or "best"
compare to specific competitors by name
nag if the user is quiet — just proceed with Rockie GPU

The user can opt into custom mode at any time by setting ROCKIE_GPU_MODE=custom; the next experiment run will see the env and trigger gpu-custom-setup for the one-time flow audit.

Picking GPU shape

Workload	Default	Notes
QE / VASP / ABINIT DFT, single SCF	1x A100_80GB	Most DFT fits in 80GB.
Large-cell DFT (>500 atoms)	4x A100_80GB	Needs MPI, use Instant Cluster.
AIMD (BOMD with QE/CP2K)	2x A100_80GB	I/O-bound; 2 pods is cheaper than 1xH100.
GROMACS / LAMMPS / OpenMM	1x A100_80GB	Single GPU saturates most MD.
PyTorch fine-tune (<7B params)	1x A100_80GB
PyTorch fine-tune (7-70B params)	4x H100_SXM	Tensor parallel; H100 SXM has NVLink.
Frontier model training	8x H200 / B200	Reach for B200 only when the user explicitly asks for it (it's the priciest SKU per GPU-hour).

Read the full file on GitHub · 229 lines

Files

What ships with it

19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

1mo ago First seen · 229 lines · 131 tokens per session scan A 5b719c528cc0

Subscribe to this mod's changes

experiment is a skill published in the GitHub repository Rockielab/rockie-codex (20 stars, last pushed 12d ago), licensed Apache-2.0. It adds 131 tokens to every session and 2,597 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Scientific

torchdrug

Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

K-Dense-AI/scientific-agent-skills · 64 tokens

arboreto

Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.

K-Dense-AI/scientific-agent-skills · 55 tokens

deepspot-m

Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.

K-Dense-AI/scientific-agent-skills · 70 tokens

pyhealth

Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer…

K-Dense-AI/scientific-agent-skills · 84 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens

nemo-mbridge-perf-expert-parallel-overlap

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.

NVIDIA/skills · 56 tokens

experiment