agents-and-testing

A guide to using AI agents and testing prompts in SolidWorks workflows. It explains agents as task specialists, skills as reusable procedures, and schemas as checks on structured results.

In plain words
What is it for?
Use it to learn the available SolidWorks agents, write prompts for tasks such as 3D-print design, and understand how their outputs are validated and logged.
Why use it?
It gives SolidWorks users a familiar way to understand agent workflows and helps them request outputs that can be checked and used in their design process.

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/agents-and-testing
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 3,721 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 $0.03721
Opus 5 $0.00000 $0.01861
Sonnet 5 $0.00000 $0.00744
Haiku 4.5 $0.00000 $0.00372

Measured 2d ago against content hash b8ea0b6b9134, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-and-testing 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.

docs/agents/agents-and-testing.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents and Prompt Testing

This guide is written for people who know SolidWorks well but are new to LLM agents and AI-assisted workflows.

What Are Agents? (Plain-Language Overview)

If you know SolidWorks, think of agents like this:

SolidWorks concept Agent equivalent
Design Intent Your prompt — what you're trying to build
Custom toolbars / macros Agents — specialists trained for specific tasks
Feature Manager checklist Schema — structured output that validates the result
Macro recorder Skill — a reusable SOP the agent follows
Feature history SQLite log — every prompt and result saved locally

You write a prompt describing what you want (material, printer, geometry constraints). The agent responds with structured, validated output — not just a chat reply — that can feed directly into your SolidWorks MCP workflow.


What Agents Are Available

Three specialist agents live in .github/agents/:

solidworks-print-architect

Use when: Designing parts for 3D printing — tolerances, snap fits, overhangs, print orientation, build volume checks.

Example output includes:

  • Material tradeoffs (PLA vs PETG vs ABS)
  • Snap-fit clearance ranges with risk level
  • Which face to put on the print bed and why
  • Build volume check against your specific printer

solidworks-mcp-skill-docs

Use when: Building SolidWorks MCP workflows, creating tutorials, planning tool sequences from sketch to feature.

Example output includes:

  • Step-by-step MCP tool call sequence
  • Decision table for tool selection
  • Troubleshooting fallbacks
  • Demo walkthrough using sample parts from your SolidWorks install

solidworks-research-validator

Use when: Fact-checking material specs, looking up printer build volumes, comparing sourcing options before committing to geometry changes.

Example output includes:

  • Short answer first
  • Evidence table with source and confidence
  • Recommended decision with risk level
  • Open questions to resolve before CAD work

Read the full file on GitHub · 458 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. 2d ago First seen · 458 lines · 0 tokens per session scan A b8ea0b6b9134

Subscribe to this mod's changes

agents-and-testing 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 3,721 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