worked-examples

A set of worked examples for rebuilding SolidWorks 3D models through an AI-agent workflow. SolidWorks is computer-aided design software, and the examples show how to inspect a model, identify its feature family, build it, and compare the result.

In plain words
What is it for?
Use it as a reference when reconstructing SolidWorks parts, reading feature trees, choosing workflows for shapes such as sheet metal, checking mass properties, and improving later prompts.
Why use it?
It helps avoid choosing the wrong modelling method and provides a repeatable way to check both the model structure and the finished shape.

Agent

Install

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.

agentmods
npx agentmods add agents/andrewbartels1/solidworksmcp-python/worked-examples
Clone the repo
git clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-python
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01615
Opus 5 $0.00000 $0.00807
Sonnet 5 $0.00000 $0.00323
Haiku 4.5 $0.00000 $0.00161

Measured yesterday against content hash cf561967cea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worked-examples 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 yesterday.

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.

docs/agents/worked-examples.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worked Examples: SolidWorks MCP + Agent Workflow

This page shows three practical reconstruction examples using the same inspect -> classify -> delegate loop:

  1. Read the original model state.
  2. Classify the feature family before writing geometry.
  3. Build with direct MCP tools only when the family supports it.
  4. Compare against mass properties and visual output.
  5. Reflect and tighten the next prompt.

Example 1: Paper Airplane (Feature-Tree Audit)

Source file: C:\Users\Public\Documents\SOLIDWORKS\SOLIDWORKS 2026\samples\learn\Paper Airplane.SLDPRT

Example 1 Stage 1: Read

open_model(file_path="...\\Paper Airplane.SLDPRT")
get_model_info()
list_features(include_suppressed=True)
get_mass_properties()
classify_feature_tree(include_suppressed=True)

Observed result:

Field Value
Family sheet_metal
Recommended workflow vba-sheet-metal
Confidence high
Why Feature tree contains sheet-metal markers and bend/fold style operations

Example 1 Stage 2: Plan

Use the feature tree and classifier output as the source of truth.
Do not simplify this into a silhouette-only extrusion.
Generate a dependency-preserving sheet-metal reconstruction strategy and flag VBA boundaries.

Example 1 Stage 3: Build

Use a delegated plan that preserves:
1. Base feature
2. Downstream bend/flange dependencies
3. Any unfold/fold state transitions

Example 1 Stage 4: Compare

Check Original Rebuild target
Family sheet_metal sheet_metal
Dependency order Base + bends/folds Same pattern
Validation signal Feature tree first Mass + image second

Example 1 Stage 5: Reflect

Worked Change next time
Classifier blocked wrong direct extrude path Always classify before geometry planning
Audit exposed true root feature Treat silhouette as secondary evidence

Example 2: Baseball Bat (Classifier-Backed Revolve)

Read the full file on GitHub · 227 lines

Changes

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.

  1. yesterday First seen · 227 lines · 0 tokens per session scan A cf561967cea6

Subscribe to this mod's changes

worked-examples 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 1,615 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens