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-modelica-graphicsWrote 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-modelica-graphics)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/annotate-modelica-graphics"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/annotate-modelica-graphics.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 | $0.00138 | $0.05408 |
| Opus 5 | $0.00069 | $0.02704 |
| Sonnet 5 | $0.00028 | $0.01082 |
| Haiku 4.5 | $0.00014 | $0.00541 |
Grade C, and why
annotate-modelica-graphics 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 7d 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.
remove the temp dir (`rm -rf "<Model-dir>/_wsm_validate_temp"`). How it starts
The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotate Modelica Graphics
This skill adds graphical annotations to a text-only Modelica .mo file so it renders as a
clean schematic in Wolfram System Modeler. It is a self-contained source transform — it
parses the .mo, classifies each class, and splices annotations back into the source:
- Category classes (packages, runnable examples, records, functions) get the idiomatic
extends Modelica.Icons.*;base — the same icons the Modelica Standard Library uses. - Leaf components / sub-circuit building blocks get a custom
Icon(graphics=…)with their connectors anchored on the icon boundary. This works for any domain — connector detection spans every Modelica Standard Library domain (electrical, mechanical, rotational/translational, MultiBody, control signals, thermal/heat, fluid, magnetic, digital, …) plus anyconnectorclass defined in the file itself. Recognized component kinds get a hand-drawn glyph (transistor, amplifier, tank, pump, valve, pipe, heat capacitor); anything else gets a generic block placeholder that you are expected to replace with an icon you draw from the component's name and description (see step 3b — this is a normal part of the workflow, not an edge case). - Connectors get their own domain-colored square icon. When the domain is recognized the color is automatic; when it isn't, you author the symbol the same way as for components.
- Composite models get an auto-laid-out Diagram: each component instance gets a
Placement, and everyconnect(…)gets an orthogonal, domain-colored connectionLine.
It is idempotent: re-running only fills in what is missing (use --force to regenerate).
By default it prints a dry-run diff; nothing is written until you pass --write.
--forceis destructive — ask the user first. It strips everyPlacement, connectionLine,Icon(...),Diagram(...), andextends Modelica.Icons.*in scope and regenerates them from scratch. The tool leaves no marker, so it matches by shape, not provenance: hand-written and hand-tuned annotations are deleted too (custom placements, manual line routing, bespoke icon graphics). Do not pass--forceon a model that may carry hand-authored graphics without first confirming with the user that discarding it is intended. Review the dry-run diff (no--write) to see exactly what would be removed before applying.
The engine is pure Python (standard library only) — no third-party packages or WSMKernelX are needed to generate the annotations. WSMKernelX is used only afterwards, as a safety gate, to confirm the edited file still flattens.
What ships with it
10 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.
- Schematic/__init__.py 691 B runs code
- Schematic/classify.py 4.3 KB runs code
- Schematic/colors.py 2.6 KB runs code
- Schematic/icon.py 11 KB runs code
- Schematic/icons_lib.py 948 B runs code
- Schematic/inject.py 15 KB runs code
- Schematic/layout.py 9.9 KB runs code
- Schematic/main.py 7.4 KB runs code
- Schematic/parser.py 1.1 KB runs code
- Schematic/routing.py 7.5 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.
- 7d ago First seen · 388 lines · 138 tokens per session scan C 9cc01bf0a9a7
annotate-modelica-graphics is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (10 stars, last pushed 18d ago), licensed MIT. It adds 138 tokens to every session and 5,408 once invoked, about $0.0007 per session on Opus 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…
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…
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.
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.
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…