diagnose-modelica

diagnose-modelica is a skill for Claude Code, Codex from WolframResearch/system-modeler-ai-toolkit. It costs 117 tokens per session (4,936 once invoked), scanned C, original, MIT.

A diagnostic workflow for Modelica model files that produces a structural and simulation report. The report can describe variables, equations, blocks, solver settings, and runtime performance when simulation data is available.

In plain words
What is it for?
Use it to analyze model structure, inspect equations and variables, review blocks and solver settings, and examine simulation performance.
Why use it?
It gives developers evidence about how a model is built and how it behaves, which helps locate structural or performance problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [`../scripts/README.md`](../scripts/README.md).*.

Good fit Use it to analyze model structure, inspect equations and variables, review blocks and solver settings, and examine simulation performance.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/WolframResearch/system-modeler-ai-toolkit
agentmods
npx agentmods add skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for diagnose-modelica

README.md
[![agentmods](https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica/github.svg)](https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica)
Your own site
<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica/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.

agentmods 80×15 button for diagnose-modelica

Your own site · 80×15
<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/diagnose-modelica.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,936 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.04936
Opus 5 $0.00059 $0.02468
Sonnet 5 $0.00023 $0.00987
Haiku 4.5 $0.00012 $0.00494

Measured 9d ago against content hash 5fae89501873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

diagnose-modelica 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`.
diagnose-modelica/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose Modelica Model

This skill generates a comprehensive diagnostic report for a Modelica model. You run the model through the bundled launcher, then turn the artifacts it leaves behind into a report with the bundled report_blocks.py / trace_variable.py scripts. The report covers variable counts, equation structure, block analysis, solver settings, and (if simulated) runtime performance.

Before you run anything

This skill drives WSMKernelX through the shared launcher ../scripts/wsm_run.py. Read the shared-conventions appendix at the end of this file first — launcher resolution, the Windows-vs-Unix shell/Python rules, the temp-dir and cleanup conventions, the JSON-array output gotcha, and the MSL 4.x dialect notes that every step below assumes.

In --mode diagnose the launcher enables the diagnostic options it needs and keeps all intermediate build artifacts for the report scripts (report_blocks.py / trace_variable.py). It works in _wsm_diagnose_temp/ next to the .mo file and leaves all artifacts there. Tell the user: "Working in temporary directory _wsm_diagnose_temp/. This will be deleted after the report is generated."

Workflow

1. Identify the model file and name

Identify the .mo file and extract the model name — see Appendix → Picking the model name. For a directory-form (multi-file) library, point --model at the library folder (not one class file) and pass the full dotted --name — see Appendix → Directory-form (multi-file) libraries.

2. Run the launcher

python3 "<scripts-dir>/wsm_run.py" --mode diagnose \
  --model "<path-to-ModelFile.mo>" --name ModelName --timeout 180

MSL is auto-detected; override with --msl yes|no or --msl-version 4.1.0. If the model uses an installed non-MSL library (e.g. Hydraulic), add --load-library <Name> — see Appendix → Using non-MSL libraries.

Read the full file on GitHub · 397 lines

Changes

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.

  1. 9d ago First seen · 397 lines · 117 tokens per session scan C 5fae89501873

Subscribe to this mod's changes

diagnose-modelica is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (10 stars, last pushed 20d ago), licensed MIT. It adds 117 tokens to every session and 4,936 once invoked, about $0.0006 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.