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-structure-noveltynpx skills add learningmatter-mit/AtomisticSkills --skill mat-structure-noveltygit 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-structure-novelty)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/mat-structure-novelty"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/mat-structure-novelty.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 | $0.00027 | $0.00886 |
| Opus 5 | $0.00014 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
mat-structure-novelty 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mat-structure-novelty
Goal
To determine whether a user-provided structure (or list of structures) has been previously reported. This is done by matching the target structure against:
- Known polymorphs in the Materials Project (MP). MP entries contain
theoreticaltags, and experimental structures will overlap with the Inorganic Crystal Structure Database (ICSD). - Any arbitrary candidate structure(s) provided by the user.
Instructions
Step 1: Execute Direct Novelty Check
Use the match_structure.py script to perform a symmetry-aware structural comparison. The script accepts a single target CIF or an entire directory of targets to run in bulk.
Option A: Automatic Materials Project Matching (Default) If you do not pass a second argument, the script will automatically query the Materials Project API for all theoretical and experimental polymorphs corresponding to the target formulas, and match your structures against them:
# Env: base-agent
python .agents/skills/mat-structure-novelty/scripts/match_structure.py generated_cifs/ --output batch_results.json
Option B: Local Candidate Matching If you want to match against a specific subset of structures (like a local ICSD dump) or just compare two specific structures, pass the explicitly downloaded candidates directory or file:
# Env: base-agent
python .agents/skills/mat-structure-novelty/scripts/match_structure.py target_structure_1.cif target_structure_2.xyz --output match_results.json
Literature Fallback (Novel/Unmatched Structures):
If the script fails to find any structural match among the candidates in the Materials Project, you should perform a literature search to see if the material has been synthesized.
When searching the literature for the structure, ONLY use the composition as input (for example, "Li3ZrCl6" or "Li3InCl6"). Do not include the space group or crystal system in the search query, as papers often do not index those exact terms in searchable abstracts.
After finding papers that report the composition, you must read the paper and compare the structure described in the literature with your candidate polymorph to determine if they match.
[!IMPORTANT] If a literature match is reported but the full text is not available (Open Access = False) and you are unable to definitively read the paper to confirm the exact reported structure matches yours, you MUST explicitly tell the user that "literature full text is not available and the structure cannot be conclusively confirmed".
What ships with it
12 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.
- examples/complex-match/candidates/mp-696128.cif 3.5 KB
- examples/complex-match/candidates/mp-696138.cif 4.0 KB
- examples/complex-match/candidates/mp-942733.cif 8.0 KB
- examples/complex-match/experimental_match.json 308 B
- examples/complex-match/known_experimental.cif 4.0 KB
- examples/complex-match/novel_match.json 268 B
- examples/complex-match/novel_structure.cif 5.0 KB
- examples/complex-match/README.md 1.1 KB
- examples/literature-fallback-match/fallback_match.json 1.6 KB
- examples/literature-fallback-match/Li2ZrCl6.cif 1.1 KB
- examples/literature-fallback-match/README.md 1.5 KB
- scripts/match_structure.py 10 KB runs code
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 · 70 lines · 27 tokens per session scan A cce6b46f09a1
mat-structure-novelty is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 886 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 2026-09-03.
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.
prepared-environment-designer
Redesign a classroom as a prepared environment optimised for independent learning, calm transitions, and material access. Use when classroom layout hinders independence or self-directed work.
gamedev-shaders
Use when authoring or debugging a shader, material, VFX, or full-screen post-process in a game engine — Godot 4.x .gdshader, Unity 6 URP/HDRP, Unreal 5.x Materials, effect recipes, shader performance. NOT gameplay or engine-API code (that is godot/unity/unreal), NOT physics (gamedev-physics), NOT build variant…
technical-artist
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || echo "=== 3D Foundations not loaded ===".
unity-shader-artist
!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true !cat skills/shared/protocols/quality-gate.md 2>/dev/null || true !cat…