Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ladla90077-web/solidworks-mcp --skill debug-simulation-failuregit clone --depth 1 https://github.com/ladla90077-web/solidworks-mcpWrote 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/ladla90077-web/solidworks-mcp/debug-simulation-failure)<a href="https://agentmods.dev/skills/ladla90077-web/solidworks-mcp/debug-simulation-failure"><img src="https://agentmods.dev/badge/skills/ladla90077-web/solidworks-mcp/debug-simulation-failure.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 | $0.00013 | $0.01343 |
| Opus 5 | $0.00006 | $0.00672 |
| Sonnet 5 | $0.00003 | $0.00269 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
Debug Simulation Failure scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Simulation Failure
What You're Actually Doing
You're helping an engineer get from "this isn't working" to either a working simulation or a clear understanding of why it can't work. The goal isn't to produce a debugging report - it's to solve the problem.
Two distinct situations:
- Simulation won't run - errors, crashes, non-convergence. The engineer has no results.
- Simulation ran but results are wrong - unexpected values, non-physical behavior, results that don't match intuition or test data.
These require different approaches. The first is about mechanics (what's preventing the solver from working). The second is about physics (what's wrong with the model's representation of reality).
When to Check In (And Why)
1. After Understanding the Problem
Before debugging, make sure you understand:
- What did they expect to happen?
- What actually happened? (Error messages, unexpected values, non-convergence)
- Has this model/simulation ever worked before? What changed?
Why this matters: "It's broken" could mean many things. A convergence failure in a nonlinear analysis is a different problem than wrong stress values in a linear static. You need to know what you're debugging.
2. When You've Identified Likely Causes
Once you've examined the model and logs, share your diagnosis before changing anything:
- What you think is wrong and why
- What you'd like to try first
- What the risk/impact of the change is
Why this matters: You can identify issues, but the engineer knows context you don't - maybe that "problem" is intentional, or maybe there's a reason they can't change it. And changes to a simulation model shouldn't be made without the engineer's knowledge.
3. After Attempting a Fix
Verify the fix actually worked:
- Did the simulation run successfully?
- Do the results make physical sense?
- Did the fix introduce new problems?
Why this matters: "It runs now" isn't the same as "it's correct." A simulation that converges to wrong answers is worse than one that fails to converge.
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 · 151 lines · 13 tokens per session scan A 382e781b290a
Debug Simulation Failure is a skill published in the GitHub repository ladla90077-web/solidworks-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,343 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. 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.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
social-physics-filter
Unified boundary enforcement, interpersonal diagnostic, and relational audit engine. Absorbs 40 psychology + 2 social protocols and all relationship case studies.
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
relax-dev-debug
Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.