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-amorphizationnpx skills add learningmatter-mit/AtomisticSkills --skill mat-amorphizationgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWhat 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 | $0.00023 | $0.01165 |
| Opus 5 | $0.00012 | $0.00583 |
| Sonnet 5 | $0.00005 | $0.00233 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
mat-amorphization 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 2d 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.
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.
Amorphorization
Goal
To generate disordered, amorphous structures from crystalline inputs using molecular dynamics (MD). This is achieved through a "melt-quench" protocol, where the material is heated above its melting point and then rapidly cooled to "freeze" the liquid-like disorder.
Protocol: Melt-Quench
The standard Computational amorphization protocol involves:
- Supercell Setup: The system must be large enough to avoid spurious periodicity effects in the amorphous state. Generally, $>100$ atoms is recommended.
- Melting (Stage A): Heat the system to $T_{melt}$. $T_{melt}$ should be significantly higher than the experimental melting point (often 1000K higher) to ensure rapid loss of crystalline memory within MD timescales.
- Equilibration (Stage A/B): Maintain the liquid at $T_{melt}$ for several picoseconds to ensure structural randomized.
- Quenching (Stage B): Cool the system linearly to the target temperature (e.g., 300K).
- Cooling Rate: A critical parameter. Typical MD cooling rates are $1-10$ K/ps ($10^{12}-10^{13}$ K/s). Slower rates yield more stable, realistic amorphous structures but are computationally expensive.
- Annealing/Equilibration (Stage C): Relax the density and local structure at the target temperature.
- Quenched/Static Relaxation (Stage D): Perform a final geometry optimization (0K) to find the local energy minimum of the amorphous state.
Instructions
1. Preparation
- Supercell: Use the
prep_supercell.pyhelper script. By default, it generates an orthorhombic conventional supercell with approximately 100 atoms, ensuring a robust starting point for amorphization.
python .agents/skills/mat-amorphization/scripts/prep_supercell.py --input crystalline.cif --output supercell.cif
- Foundation Potential: Select a robust model like
MACE-MP-largeorCHGNetusing themcp_mace_load_model(or similar) tool.
2. Execution (The Melt-Quench Cycle)
Amorphization is performed by calling the run_md tool in a sequence:
What ships with it
6 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.
- 2d ago First seen · 76 lines · 23 tokens per session scan A 6666ff7b1498
mat-amorphization is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (154 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 1,165 once invoked, about $0.0001 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 2026-08-30.
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.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…