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/annotate-control-panelWrote 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/annotate-control-panel)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/annotate-control-panel"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/annotate-control-panel/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/annotate-control-panel"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/annotate-control-panel.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 | $0.00142 | $0.06842 |
| Opus 5.5 | $0.00057 | $0.02737 |
| Sonnet 5.5 | $0.00028 | $0.01368 |
| Haiku 4.5 | $0.00014 | $0.00684 |
Grade C, and why
annotate-control-panel 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotate Control Panel
This skill writes the Wolfram control-panel (Explore) annotation into a Modelica .mo file so a
model carries its own interactive panels — the sliders, checkboxes, input fields and popup menus that
Simulation Center's Explore view shows for driving parameters and start values, plus the plots to
display:
annotation(__Wolfram(ControlPanels(
Panel(
identifier = "id1",
title = "Controller tuning",
elements = {
Slider(variable = Kp, label = "Proportional gain", min = 0, max = 100),
Slider(variable = Kd, min = 0, max = 20, scale = Log()),
Checkbox(variable = useFeedforward, label = "Feedforward")},
figures = {"response"})));
It is a self-contained source transform: Claude assembles a control-panel spec (JSON) — from the
user's request, or suggested from the model's parameters — and the Python engine renders it to the
__Wolfram(ControlPanels(...)) vendor annotation and splices it into the class annotation. The engine
is pure Python (standard library only); WSMKernelX is used only afterwards as a validation gate.
This is a vendor-specific annotation (Modelica spec §18.1): other tools ignore it and preserve it
on save, and it does not affect flattening — it just tells System Modeler how to build the Explore
panels. It sits directly inside annotation(...), as a sibling of experiment and Documentation
(never nested inside Documentation).
It is idempotent: a class that already has control panels is skipped unless you pass --force
(which strips the old ControlPanels block and regenerates). By default it prints a dry-run diff;
nothing is written until --write.
--forceis destructive — ask the user first. It deletes the class's existing control panels before regenerating, so any hand-tuned panels there are lost. Don't pass--forceon a class that already carries control panels without confirming that discarding them is intended. Review the dry-run diff (no--write) to see exactly what would be removed.
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.
- ControlPanel/__init__.py 533 B runs code
- ControlPanel/discover.py 4.3 KB runs code
- ControlPanel/inject.py 3.7 KB runs code
- ControlPanel/main.py 9.9 KB runs code
- ControlPanel/panels.py 9.3 KB runs code
- ControlPanel/parser.py 1.1 KB runs code
- ControlPanel/simvars.py 1.8 KB runs code
- ControlPanel/suggest.py 2.4 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.
- 9d ago Changed · +4 lines df5cb70b1d98
- 23d ago Changed · +111 lines f789315499e8
- 1mo ago First seen · 402 lines · 142 tokens per session scan C b403af3928df
annotate-control-panel is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (17 stars, last pushed 9d ago), licensed MIT. It adds 142 tokens to every session and 6,842 once invoked, about $0.0006 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 2026-08-31.
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…