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 agentmods add agents/andrewbartels1/solidworksmcp-python/ai-assisted-design-workflowgit clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-pythonWhat 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 | $0.00000 | $0.03938 |
| Opus 5 | $0.00000 | $0.01969 |
| Sonnet 5 | $0.00000 | $0.00788 |
| Haiku 4.5 | $0.00000 | $0.00394 |
Grade A, and why
ai-assisted-design-workflow 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 2d 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Assisted Design: Build Faster in SolidWorks
You know SolidWorks. You know the click path for a boss extrude, you know what a fully-defined sketch looks like, and you have a feel for which features will cause a rebuild error before you even run it.
This workflow keeps all of that knowledge and removes the slow parts — navigating menus, re-entering dimensions, rebuilding after a typo. Instead you describe what you're building in plain language, the LLM proposes the exact tool call sequence, you review it in ten seconds, and SolidWorks builds it.
The goal is faster iteration on your designs — not just recreating sample parts. The sample parts (Paper Airplane.SLDPRT, Baseball Bat.SLDPRT, the U-Joint) appear throughout because they're excellent practice targets: the finished .SLDPRT file exists, so you can open the original, read its feature tree, and check whether your AI-assisted build produced the same result. Once you're comfortable with the loop, apply it to your own work.
What You Need
| Requirement | How to get it |
|---|---|
| SolidWorks installed and open | — |
| MCP server running | .\dev-commands.ps1 dev-run |
| Claude Code or VS Code Copilot Chat | Claude Code setup · VS Code setup |
| Python virtualenv activated | .\dev-commands.ps1 dev-install once, then auto |
Quick server check — if the MCP server is running, this returns immediately:
.\.venv\Scripts\python.exe -c "from solidworks_mcp.server import create_server; print('OK')"
The Design Loop
flowchart LR
D(["1 - Describe<br/>Shape + dimensions<br/>in plain text"])
P(["2 - Plan<br/>LLM proposes<br/>tool call sequence"])
R(["3 - Review<br/>You read the list<br/>and approve"])
E(["4 - Execute<br/>Claude Code runs<br/>the MCP tools"])
C(["5 - Check<br/>Visual or<br/>feature tree"])
I(["6 - Iterate<br/>Adjust and re-run<br/>only what changed"])
D --> P --> R --> E --> C --> I
I -->|new idea or fix| D
style R fill:#fff3cd,stroke:#ffc107
style C fill:#fff3cd,stroke:#ffc107
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.
- 2d ago First seen · 434 lines · 0 tokens per session scan A 94213ee57338
ai-assisted-design-workflow is an agent published in the GitHub repository andrewbartels1/SolidworksMCP-python (65 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,938 tokens. 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.