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/mat-dft-lobsternpx skills add learningmatter-mit/AtomisticSkills --skill mat-dft-lobstergit 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/mat-dft-lobster)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/mat-dft-lobster"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/mat-dft-lobster.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 | $0.00034 | $0.01065 |
| Opus 5 | $0.00017 | $0.00532 |
| Sonnet 5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
mat-dft-lobster 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mat-dft-lobster
Goal
To calculate advanced chemical bonding properties—like Crystal Orbital Hamilton Populations (COHP), atomic charges, projected DOS, and bonding integrands (ICOHP)—by projecting converged plane-wave Density Functional Theory (DFT) wavefunctions onto a localized, atomic-like basis set using the LOBSTER code.
Background
Standard plane-wave DFT (e.g., VASP) distributes electron density uniformly across reciprocal space, which is computationally robust but lacks explicit chemical intuition regarding localized bonds. LOBSTER (Local Orbital Basis Suite Towards Electronic-Structure Reconstruction) takes the massive WAVECAR from VASP and projects it back to an atomic orbital basis to recover classical chemical bonding insights.
Because WAVECAR files are extremely large (often tens or hundreds of gigabytes), LOBSTER analysis must be performed on the same remote node directly after the VASP static loop. The atomate2 VaspLobsterMaker automates this sequentially (Relax -> Static -> Lobster) and ensures the massive WAVECAR is deleted once the projection completes.
Installation
LOBSTER is free to download for non-commercial use from http://www.cohp.de/.
To use this skill, deploy the compiled lobster binary to your remote HPC worker or local testing environment and ensure its path is exported in your environment PATH. All required Python packages (lobsterpy, ijson) are already provided by the atomate2-agent environment.
Instructions
1. Generate and Execute the Workflow
To submit a LOBSTER workflow, utilize the built-in MCP tool. This natively maps the VaspLobsterMaker directed acyclic graph (DAG) to your HPC resources:
Tool: mcp_atomate2_run_atomate2_vasp_calculation
Arguments:
structures_path: Path to your POSCAR or CIF.calculation_type:"lobster"execution_mode:"remote"(to execute on the HPC worker)
CRITICAL: Do not run this locally unless you are purely generating testing DAGs (check_only=True). The generated flow contains heavy VASP iterations and high-memory LOBSTER matrix projections.
What ships with it
4 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 · 76 lines · 34 tokens per session scan A f58131fb49b5
mat-dft-lobster is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,065 once invoked, about $0.0002 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
cd-calculator
Python calculators for geometry analysis, structural checking, solar calculations, panel optimization, mesh analysis, material estimation, and fabrication cost estimation for AEC computational design.
cd-calculator
Python calculators for geometry analysis, structural checking, solar calculations, panel optimization, mesh analysis, material estimation, and fabrication cost estimation for AEC computational design.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.