agentmods.dev

experiment

experiment is a skill for Claude Code from Rockielab/rockie-claude. It costs 141 tokens per session (3,769 once invoked), scanned A, original, Apache-2.0.

A tool for sending materials-science or machine-learning calculations to Rockie GPU capacity. It chooses GPU resources and runs the supplied job there.

In plain words
What is it for?
Use it for density-functional theory calculations, molecular dynamics, model training or fine-tuning, and batches of model inference that need GPUs.
Why use it?
It keeps GPU-heavy work off the agent’s own computer and prevents unsuitable local execution. It also handles job submission and monitoring from a natural-language request.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

Part of the rockie-claude plugin — 29 skills, 1 MCP server shipped together

not rated 21repo 1mo ago A scan 141 tokens original Apache-2.0

Good fit Use it for density-functional theory calculations, molecular dynamics, model training or fine-tuning, and batches of model inference that need GPUs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rockielab/rockie-claude/experiment
View source ↗ Rockielab/rockie-claude
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-claude --skill experiment
Clone the repo
git clone --depth 1 https://github.com/Rockielab/rockie-claude

Made for: Claude Code.

Or install rockie-claude, the plugin that ships this one along with the rest of its 29 skills, 1 MCP server.

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.

agentmods badge for experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/rockielab/rockie-claude/experiment/github.svg)](https://agentmods.dev/skills/rockielab/rockie-claude/experiment)
Your own site
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/experiment"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/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.

agentmods 80×15 button for experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/rockielab/rockie-claude/experiment"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,769 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.03769
Opus 5 $0.00071 $0.01885
Sonnet 5 $0.00028 $0.00754
Haiku 4.5 $0.00014 $0.00377

Measured 10d ago against content hash d9743a56c68f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

artifact to `runtime/submit.py` (don't shell out to curl
project-harness/skills/experiment/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 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.

Local execution FORBIDDEN

Torch / triton / CUDA execution, weight downloads (HF), training, fine-tuning, heavy synthetic-data generation NEVER run on the orchestrator host or the Fly tenant runtime — they run ONLY on the Rockie GPU pod that this skill provisions.

The PreToolUse hook role-pre-bash-guard.sh blocks such Bash invocations on the orchestrator; the runtime image's torch/__init__.py (plus triton, tensorflow, jax) stub raises on import inside Fly tenants. Both layers point at POST $ROCKIELAB_API_URL/api/jobs/submit with a base64-encoded script. See rockie-workspace#457.

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 invokes /experiment directly.

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

First-experiment GPU disclosure

Before submitting the user's FIRST experiment in a workspace, the agent emits one neutral sentence before proceeding:

Rockie provisions the GPU pod for this experiment, and the per-hour price it quotes already includes the platform overhead; proceeding unless you want to change the scope.

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
  • offer BYO/custom GPU mode or a router bypass
  • nag if the user is quiet — just proceed with Rockie GPU

CLI nudge for repeatable job workflows

Follow skills/cli-guidance.md for canonical Rockie CLI commands and rate limiting. When the user is launching repeated runs, setting up a headless agent/CI workflow, or asking how to automate job submission, advise the Rockie CLI at most once per session for that topic and include the exact setup command from the shared guidance.

Read the full file on GitHub · 336 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.

  1. 10d ago First seen · 336 lines · 141 tokens per session scan A d9743a56c68f

Subscribe to this mod's changes

experiment is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 141 tokens to every session and 3,769 once invoked, about $0.0007 per session on Opus 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.

Claude CodeData and AIScientificagent-harnessai-researchanthropicautonomous-researchclaude
Related

Other skills, from other repositories

saelens

Train sparse autoencoders to interpret model features.

NousResearch/hermes-agent · 14 tokens

nnsight-remote-interpretability

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

davila7/claude-code-templates · 59 tokens

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

davila7/claude-code-templates · 52 tokens

esmfold2

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…

aipoch/open-science · 223 tokens

scgpt

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…

aipoch/open-science · 89 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens