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 skills add WolframResearch/system-modeler-ai-toolkit --skill search-modelica-docsgit clone --depth 1 https://github.com/WolframResearch/system-modeler-ai-toolkitWrote 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/search-modelica-docs)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/search-modelica-docs"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/search-modelica-docs.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 | $0.00242 | $0.01807 |
| Opus 5 | $0.00121 | $0.00903 |
| Sonnet 5 | $0.00048 | $0.00361 |
| Haiku 4.5 | $0.00024 | $0.00181 |
Grade A, and why
search-modelica-docs 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Modelica & System Modeler Documentation (BM25)
A self-contained, offline documentation search. It ranks passages with BM25 (pure Python standard library — no third-party packages, no network, no API) over three prebuilt corpora and returns the matching chunks with their citation URLs. Use it to ground answers in real documentation instead of recalling from memory.
The three corpora (and how to route)
The content covers the Modelica language, the System Modeler tool, and the Modelica Standard Library — pick the corpus by what the user means:
--corpus value |
Covers | Backing corpora |
|---|---|---|
modelica |
The Modelica language — syntax, semantics, the normative specification | spec |
systemmodeler (or sm) |
Wolfram System Modeler, the tool — building/simulating models, GUI, tutorials, what's-new | docs |
msl (or library) |
The Modelica Standard Library — component/block docs, exact parameter names, example models, annotation-stripped source | msl |
all (default) |
Everything | spec + docs + msl |
spec |
Modelica Language Specification (normative) | spec |
docs |
System Modeler documentation | docs |
Routing guidance:
- Language questions ("how does
whenwork", "is this valid Modelica", "what's the rule for...") →--corpus modelica. - Tool questions ("how do I simulate / plot / use the GUI in System Modeler",
"what's new in 15") →
--corpus systemmodeler. - Library questions ("which block gives me an anti-windup PID", "what are the
parameters of
Inertia", "show an example wiring a spring-damper") →--corpus msl. Also use this while writing a model with MSL components to confirm parameter names andconnect()patterns. - When unsure, use
all(the default) — a question often spans corpora, and the results are tagged so you can see where each came from. Butmslis by far the largest corpus (~4,700 chunks vs ~900 for the other two), so if you know the question is about the language or the tool, route to that corpus — it keeps library chunks from crowding out the answer.
What ships with it
8 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.
- 8d ago First seen · 114 lines · 242 tokens per session scan A 9d8bf37e7260
search-modelica-docs is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (10 stars, last pushed 19d ago), licensed MIT. It adds 242 tokens to every session and 1,807 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
proof-writer
A tool for writing or checking rigorous mathematical proofs for claims such as theorems, lemmas, propositions, and corollaries.
tooluniverse-organic-chemistry
Organic chemistry reasoning guide for reaction product prediction, mechanism analysis (electrophilic/nucleophilic substitution, addition, elimination, pericyclic, radical), and spectroscopy interpretation (1H/13C NMR, IR, MS). Reasons from first principles (electron flow, kinetic vs thermodynamic) rather than…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…
edu-chem-reaction
A guide for turning a chemical reaction into a self-contained interactive 3D web demonstration. It shows molecules changing while also displaying the balanced equation, explanations, atom counts, and optionally an energy curve.
edu-solid-geometry
A guide for turning a three-dimensional geometry problem into a self-contained interactive web lesson. It combines step-by-step mathematical working with a rotatable 3D model made with Three.js.