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 skills/learningmatter-mit/atomisticskills/ml-mlip-nvalcheminpx skills add learningmatter-mit/AtomisticSkills --skill ml-mlip-nvalchemigit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote 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/skills/learningmatter-mit/atomisticskills/ml-mlip-nvalchemi)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/ml-mlip-nvalchemi"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/ml-mlip-nvalchemi.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 | $0.00059 | $0.05442 |
| Opus 5 | $0.00030 | $0.02721 |
| Sonnet 5 | $0.00012 | $0.01088 |
| Haiku 4.5 | $0.00006 | $0.00544 |
Grade A, and why
ml-mlip-nvalchemi 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 today.
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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ml-mlip-nvalchemi
Goal
Exploit NVIDIA's NValchemi toolkit to run energy/force/stress predictions, geometry relaxations, and molecular dynamics for a batch of structures in a single GPU-parallel forward pass, instead of N sequential CPU loops. This is automatically activated when nvalchemi-toolkit is installed in the environment — the existing MCP tool surface (static_calculation, relax_structure, run_md) passes a list of structures and dispatches to the NValchemi backend transparently.
Background
NValchemi provides batched dynamics integrators (FIRE, NVT Nose-Hoover, NPT, etc.) and a BaseModelMixin interface. AtomisticSkills wraps each MLIP in a BaseModelMixin-compatible class:
| MLIP | NValchemi wrapper | Location |
|---|---|---|
| MACE | nvalchemi.models.mace.MACEWrapper |
upstream (nvalchemi-toolkit) |
| MatGL TensorNet | matgl.ext._alchmtk.TensorNetWrapper |
matgl package |
| MatGL M3GNet | M3GNetWrapper |
src/utils/mlips/nvalchemi/matgl_wrappers.py |
| MatGL CHGNet | CHGNetWrapper |
src/utils/mlips/nvalchemi/matgl_wrappers.py |
| MatGL QET | QETWrapper |
matgl package |
| FairChem UMA | FairChemWrapper |
src/utils/mlips/nvalchemi/fairchem_nv.py |
The dispatch lives in src/utils/mlips/base.py:
static_calculation(list)→_batch_static_nvalchemi()→ single batched forwardrelax_structure(list)→_batch_relax_nvalchemi()→ batched FIRErun_md(list)→_batch_md_nvalchemi()→ batched NVT/NVE/NPT integrator
Inflight batching (relaxation)
For relax_structure, there are three execution backends selected automatically:
_batch_relax()
├─ nvalchemi available AND model loads?
│ YES → _batch_relax_nvalchemi()
│ └─ sum(atoms) > max_batch_atoms AND model._nvalchemi_supports_inflight?
│ YES → _batch_relax_nvalchemi_inflight() ← rolling GPU window
│ NO → fixed-batch NValchemi ← all structures at once
│ NO → _batch_relax_sequential() ← plain ASE FIRE, one by one
What ships with it
3 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.
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.
- today First seen · 312 lines · 59 tokens per session scan A 0409209ee8f3
ml-mlip-nvalchemi is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 5,442 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
HomeSafe-Bench
VLM indoor safety hazard detection benchmark inspired by HomeSafeBench (arXiv 2509.23690).
depth-estimation
Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch).
start-experiment
Start the autoresearch optimization loop for a specific model + lane. Resolves the hierarchical program.md (root → model → lane), asks the user for hardware (local TPU VM or GKE cluster of a specified TPU type + topology), discovers available clusters from .env/, checks occupancy with USERPREFIX-aware attribution…