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/minimize-modelica-bugWrote 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/minimize-modelica-bug)<a href="https://agentmods.dev/skills/wolframresearch/system-modeler-ai-toolkit/minimize-modelica-bug"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/minimize-modelica-bug/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/minimize-modelica-bug"><img src="https://agentmods.dev/badge/skills/wolframresearch/system-modeler-ai-toolkit/minimize-modelica-bug.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 | $0.00170 | $0.06560 |
| Opus 5.5 | $0.00068 | $0.02624 |
| Sonnet 5.5 | $0.00034 | $0.01312 |
| Haiku 4.5 | $0.00017 | $0.00656 |
Grade C, and why
minimize-modelica-bug 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimize a Modelica Compiler Bug
A compiler failure is a fault in System Modeler itself rather than in the
model. Examples are an Internal error, generated code that does not compile,
and a simulator that stops with an internal error. This skill shrinks the
failing model to the smallest one that still fails with the same message, and
writes a short report the user can send to Wolfram support. A small
reproduction gets a bug fixed; a 5,000-line proprietary model usually does not.
Ordinary model errors are not compiler failures: type, lookup and balance errors,
failed assertions, or a solver giving up. Fix those in the model instead, using
validate-modelica or diagnose-modelica.
Before you run anything
This skill drives WSMKernelX through the shared launcher
../scripts/wsm_run.py and the reducer ../scripts/minimize_mo.py. Read
the shared-conventions appendix at the end of this file first. It covers launcher
resolution, the Windows-vs-Unix shell/Python rules, and the temp-dir and
line-ending conventions that every step below assumes.
The reducer never touches the user's files. It works on copies in
_wsm_minimize_temp/ next to the model. Tell the user: "Working in temporary
directory _wsm_minimize_temp/; your model is not modified."
Workflow
1. Confirm that it is a compiler failure
Identify the model file and name — see Appendix → Picking the model name and, for a multi-file library, Appendix → Directory-form (multi-file) libraries. Then run it once:
python3 "<scripts-dir>/wsm_run.py" --mode simulate \
--model "<path-to-ModelFile.mo>" --name ModelName --json
"compiler_failure"in the printed JSON is notnull: this is a compiler failure. Note itshead(the part of the message that identifies the fault) and the System Modelerversion."compiler_failure"isnull: it is not a compiler failure. Tell the user so, show the ordinary error the launcher printed, and help fix the model instead.
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 c2d3dbd74c81
- 23d ago First seen · 501 lines · 170 tokens per session scan C de65ece52b58
minimize-modelica-bug is a skill published in the GitHub repository WolframResearch/system-modeler-ai-toolkit (17 stars, last pushed 9d ago), licensed MIT. It adds 170 tokens to every session and 6,560 once invoked, about $0.0007 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
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.