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/simulate-modelica-realtimeWrote 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/simulate-modelica-realtime)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/simulate-modelica-realtime"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/simulate-modelica-realtime/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/simulate-modelica-realtime"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/simulate-modelica-realtime.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 | $0.00198 | $0.06671 |
| Opus 5.5 | $0.00079 | $0.02668 |
| Sonnet 5.5 | $0.00040 | $0.01334 |
| Haiku 4.5 | $0.00020 | $0.00667 |
Grade C, and why
simulate-modelica-realtime scanned grade C with 1 finding 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.
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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk to a simulation executable
Every simulation System Modeler builds is an executable plus a .sim settings file, and every
running simulation has a built-in TCP server. A client can start, pause, resume and stop the run,
set top-level inputs at any time, set tunable parameters while the solver runs, read any variable,
and subscribe to variables that are then streamed while it runs. This skill does that with the
stdlib-only client <scripts-dir>/wsmsim.py and its command line <scripts-dir>/wsm_realtime.py.
Resolve <scripts-dir> as in Appendix → Locating the launcher,
and follow its shell and Python rules per OS.
1. Get a simulation to talk to
Either of these works:
- Launch an executable. Build the model with the simulate-modelica skill, and keep
_wsm_simulate_temp/next to the model: it holds<Model>_<id>.exeand its.sim. Give that directory as<target>with--model ModelName(or the executable path) below; the CLI starts it in server mode, paced to the wall clock, on a free port. - Attach to a running simulation. A simulation started in Simulation Center, or by hand with
<Model>_<id>.exe -f <Model>_<id>.sim -server 127.0.0.1:7000, is already listening; the simulation log shows the address (Server listening on 127.0.0.1:<port>). Pass--attach host:portinstead of a target. An attached client never stops the simulation when it disconnects, so several clients can share one run.
Only top-level input variables can be changed while the solver runs, and only tunable
parameters after the start. If the model exposes nothing to steer, add input Real u(start = ...)
variables (or a wrapper model) for the quantities the user wants to drive, and make the display
quantities top-level outputs; validate with validate-modelica.
2. Inspect the interface as the server sees it
python3 "<scripts-dir>/wsm_realtime.py" info <target> --model ModelName
Prints inputs and their start values, outputs, tunable parameters and states. Use these exact
names below; nested names use dots (load.p), array elements [k]. Every streamed sample already
carries the simulation time, so do not subscribe to time.
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 2f063a947910
- 23d ago First seen · 468 lines · 198 tokens per session scan C 5c1ec744ad53
simulate-modelica-realtime is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (17 stars, last pushed 9d ago), licensed MIT. It adds 198 tokens to every session and 6,671 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
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…