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-reaction-networknpx skills add learningmatter-mit/AtomisticSkills --skill mat-reaction-networkgit 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-reaction-network)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/mat-reaction-network"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/mat-reaction-network.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 5.1 | $0.00022 | $0.00776 |
| Opus 5 | $0.00011 | $0.00388 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
mat-reaction-network 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material Reaction Network Prediction
Goal
To predict the optimal sequence of thermodynamically favorable chemical reactions (pathways) needed to synthesize a target generic solid-state material from a set of starting precursors. This skill enumerates large, competitive reaction networks and solves for minimum-energy paths using the materialsproject/reaction-network code and Materials Project API thermodynamics data.
Instructions
1. Reaction Enumeration
Explore the landscape of competing reactions within a specific chemical system by explicitly generating balanced equations.
# Env: base-agent
python .agents/skills/mat-reaction-network/scripts/enumerate_reactions.py --chemsys Ba-Ti-O --enumerator-type basic_open --open-phases O2 --temperature 1000 --limit 10
--chemsys: The chemical system to restrict search to.--enumerator-type: The algorithm used to propose reactions (basic,basic_open,minimize_gibbs,minimize_grand_potential).--open-phases: (Specific tobasic_open) allow materials to be freely consumed or produced from an infinite reservoir (like environmental O2).--temperature: Synthesis temperature (Kelvin), affects Gibbs adjustments.--limit: Maximum number of elementary reactions to print.
2. Pathfinding and Solving Syntheses
To resolve a complete list of step-by-step reactions that convert specific starting precursors into a target compound, use the pathway solver script.
# Env: base-agent
python .agents/skills/mat-reaction-network/scripts/find_pathways.py --target BaTiO3 --precursors BaO TiO2 --temperature 1000 --k-paths 5
--target: The desired final functional material.--precursors: One or more starting materials (e.g., oxides or carbonates).--byproducts: Optional allowed volatile byproducts (e.g.,CO2,H2O) escaping into the atmosphere.--k-paths: Number of different candidate elementary pathways to yield.
Examples
Finding pathways to synthesize Yttrium Manganite from carbonates and chlorides:
# Env: base-agent
python .agents/skills/mat-reaction-network/scripts/find_pathways.py \
--target YMnO3 \
--precursors YCl3 Mn2O3 Li2CO3 \
--byproducts LiCl CO2 \
--temperature 923 \
--k-paths 5
What ships with it
11 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/1_predict_liznpo4/pair_a_output.json 28 KB
- examples/1_predict_liznpo4/pair_b_output.json 1.8 KB
- examples/1_predict_liznpo4/pair_c_output.json 7.5 KB
- examples/1_predict_liznpo4/README.md 3.8 KB
- examples/1_predict_liznpo4/run.sh 1003 B runs code
- examples/2_predict_libabo3/predicted_output.json 24 KB
- examples/2_predict_libabo3/README.md 1.9 KB
- examples/2_predict_libabo3/run.sh 876 B runs code
- examples/2_predict_libabo3/traditional_output.json 11 KB
- scripts/enumerate_reactions.py 5.5 KB runs code
- scripts/find_pathways.py 8.6 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.
- 2d ago First seen · 64 lines · 22 tokens per session scan A e16a59bf9551
mat-reaction-network is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (161 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 776 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.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
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…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.