Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WolframResearch/system-modeler-ai-toolkitnpx agentmods add skills/wolframresearch/system-modeler-ai-toolkit/modelica-model-architectureWrote 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/wolframresearch/system-modeler-ai-toolkit/modelica-model-architecture)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/modelica-model-architecture"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/modelica-model-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/modelica-model-architecture"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/modelica-model-architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00203 | $0.08996 |
| Opus 5.5 | $0.00081 | $0.03598 |
| Sonnet 5.5 | $0.00041 | $0.01799 |
| Haiku 4.5 | $0.00020 | $0.00900 |
Grade D, and why
modelica-model-architecture scanned grade D with 2 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 9d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- [ ] Each class **validates**, and examples **build/simulate**, without warnings Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
shell-agnostic. For cleanup use `Remove-Item -Recurse -Force`, not `rm -rf`. How it starts
The opening of the file, as written. The whole thing — 680 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WSM / Modelica model architecture
Use this when creating or restructuring a WSM/Modelica model or library — before writing equations. This skill covers the architecture and structuring decisions that come first (sections 1-7), then the library conventions — naming, plots, documentation HTML, testing, icons, library shape — that a model or library must meet before it is "done" (sections 8-9). Read sections 8-9 before declaring a library done.
The default in Modelica is object-oriented decomposition into reusable components. Reach for a flat all-in-one model only under the explicit exception in section 5.
Working method
- Propose a step-by-step plan and wait for explicit approval before any edit. Present it as numbered steps.
- Offer the user a "one-shot" option: they may approve the whole sequence at once and have you execute it end to end without stopping between steps.
- If the user takes the one-shot option, first state the choices you will make
autonomously — the decisions you would otherwise have stopped to ask about
(e.g. authoring
GettingStarted/Introduction, storing example result plots, adding icons, how far to decompose). One-shot suppresses the questions, not the decisions; surfacing the defaults up front lets the user veto before you build. - When creating a library, recommend a parallel test library from the start. Add a unit test for each component as you build it — not at the end.
- Never delete the user's model files to "start clean." When the toolchain errors, fix the code forward — a validate/simulate failure is almost always a wrong name or missing load, not a reason to throw the work away. Deleting files to reset loses work and is rarely what the user wants.
1. Reuse before building (priority order)
When you need a component (or a connector), look in this order and only build new if nothing fits:
- MSL — the Modelica Standard Library.
- The user's own Git-repo libraries (e.g. what lives in their repo).
- Wolfram libraries — bundled / add-on WSM libraries.
- Your own component — last resort.
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.
- 9d ago Changed · +4 lines a61173b90a3b
- 23d ago Changed · +380 lines · -19 tokens per session scan B → D 0ee870e2d8d0
- 1mo ago First seen · 296 lines · 222 tokens per session scan B 439c2d9cf79c
modelica-model-architecture is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (17 stars, last pushed 9d ago), licensed MIT. It adds 203 tokens to every session and 8,996 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it D with 2 findings (strips warnings and disclaimers, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports 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
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
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…