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/reverse-engineering-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 | $0.03049 |
| Opus 5 | $0.00000 | $0.01524 |
| Sonnet 5 | $0.00000 | $0.00610 |
| Haiku 4.5 | $0.00000 | $0.00305 |
Grade A, and why
reverse-engineering-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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From Screenshot to SolidWorks: The Image-First Reconstruction Workflow
This tutorial shows how to take a screenshot or rendered image of a part — including the sample parts that ship with SolidWorks — and use prompting to recreate it from scratch using the MCP server.
The approach mirrors what an engineer does by eye: look at the shape, describe it in terms the CAD system understands, and build it feature by feature.
The sample parts used throughout this guide live at:
C:\Users\Public\Documents\SOLIDWORKS\SOLIDWORKS 2026\samples\learn\
The Three-Prompt Pattern
Every reconstruction follows the same shape regardless of part complexity:
Prompt 1 — Describe → Prompt 2 — Plan → Prompt 3 — Build & Test
"What do you see in → "Turn that description → "Execute each step and
this image?" into an ordered MCP confirm the result matches
tool sequence." the reference image."
The image goes into Prompt 1. Everything after that is text, but for any sample part where the original file is available you should treat the image description as provisional. Before finalizing a reconstruction plan, open the original part and read the feature tree.
Getting a Reference Image
Before prompting, you need a clear isometric or front-view image of the part.
Option A — Screenshot from SolidWorks directly
Open the sample part in SolidWorks (File > Open), orient the view to isometric (Ctrl+7), and press Print Screen or use the Snipping Tool. Save as a .png or .jpg.
Option B — Export from the MCP server
If the MCP server is running and SolidWorks is open with the file loaded:
open_model(file_path=r"C:\Users\Public\Documents\SOLIDWORKS\SOLIDWORKS 2026\samples\learn\Paper Airplane.SLDPRT")
export_image(file_path="paper_airplane_ref.jpg", format_type="jpg")
close_model(save=False)
The image is saved to disk and can be dragged into Claude Code or uploaded to any vision-capable chat interface.
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 · 354 lines · 0 tokens per session scan A 9da85d7d8eab
reverse-engineering-workflow is an agent published in the GitHub repository andrewbartels1/SolidworksMCP-python (65 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,049 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
deployment-specialist
Handles all deployment operations.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.