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/diagnose-modelicaWrote 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/diagnose-modelica)<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.
<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>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 | $0.00154 | $0.09399 |
| Opus 5.5 | $0.00062 | $0.03760 |
| Sonnet 5.5 | $0.00031 | $0.01880 |
| Haiku 4.5 | $0.00015 | $0.00940 |
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`. How it starts
The opening of the file, as written. The whole thing — 713 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.
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 2a174ce168eb
- 23d ago Changed · +312 lines · +37 tokens per session 33f33326c496
- 1mo ago First seen · 397 lines · 117 tokens per session scan C 5fae89501873
diagnose-modelica is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (17 stars, last pushed 9d ago), licensed MIT. It adds 154 tokens to every session and 9,399 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
trace
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.
pos-tagging-fixes
Diagnose and fix part-of-speech tagging in the compromise source repository. Choose between lexical data, ambiguity clues, indexed neighbour rules, preTagger logic, and postTagger patterns with attention to execution order, side effects, runtime, and bundle size. Use for internal tagging changes, not ordinary…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
nonlinear-solvers
Select and configure nonlinear solvers for f(x)=0 or min F(x). Use for Newton methods, quasi-Newton (BFGS, L-BFGS), Broyden, Anderson acceleration, diagnosing convergence issues, choosing line search vs trust region, and analyzing Jacobian quality.
linear-solvers
Select and configure linear solvers for systems Ax=b in dense and sparse problems. Use when choosing direct vs iterative methods, diagnosing convergence issues, estimating conditioning, selecting preconditioners, or debugging stagnation in GMRES/CG/BiCGSTAB.
numerical-stability
Analyze and enforce numerical stability for time-dependent PDE simulations. Use when selecting time steps, choosing explicit/implicit schemes, diagnosing numerical blow-up, checking CFL/Fourier criteria, von Neumann analysis, matrix conditioning, or detecting stiffness in advection/diffusion/reaction problems.