SolidworksMCP-python: Agent for Claude Code

.github/agents/solidworks-mcp-skill-docs.agent.md

SolidWorks MCP Skill and Docs Engineer is an agent for Claude Code from andrewbartels1/SolidworksMCP-python. It costs 62 tokens per session (762 once invoked), scanned A, original, MIT.

A specialist guide for building SolidWorks MCP workflows and documentation. SolidWorks is computer-aided design software, and MCP connects an AI agent to tools that can work with it.

In plain words
What is it for?
Use it to create or refine SolidWorks skills and services, improve tool-selection guidance, reconstruct parts from feature trees, and write or correct local documentation and demos.
Why use it?
It helps turn vague design requests into clear tool choices, delegation rules, safeguards, and reproducible workflows instead of relying on guesses from an image.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is andrewbartels1/SolidworksMCP-python's own configuration. It tells Claude Code how to work on SolidworksMCP-python itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SolidworksMCP-python configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andrewbartels1/SolidworksMCP-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andrewbartels1/SolidworksMCP-python/main/.github/agents/solidworks-mcp-skill-docs.agent.md
Clone the repo
git clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-python

Made for: Claude Code.

Wrote 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.

agentmods badge for SolidWorks MCP Skill and Docs Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs/github.svg)](https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs)
Your own site
<a href="https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs"><img src="https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for SolidWorks MCP Skill and Docs Engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs"><img src="https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/solidworks-mcp-skill-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00062 $0.00762
Opus 5.5 $0.00025 $0.00305
Sonnet 5.5 $0.00012 $0.00152
Haiku 4.5 $0.00006 $0.00076

Measured 1mo ago against content hash ae8dcc1cd336, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SolidWorks MCP Skill and Docs Engineer 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 1mo 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.

.github/agents/solidworks-mcp-skill-docs.agent.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist in SolidWorks MCP agentic workflows and technical documentation for the local SolidworksMCP-python project.

Primary Scope

  1. Skill and service engineering
  • Create and refine reusable skills/services that help LLMs select the best SolidWorks MCP tool with fewer retries.
  • Turn ambiguous user intents into explicit decision logic, guardrails, fallback steps, and delegation boundaries.
  • Propose robust tool-selection heuristics with clear assumptions and failure handling.
  • Encode feature-tree-first workflows for reconstruction tasks so the main agent does not guess from appearance when the original part is available.
  1. Local MCP workflow support
  • Align recommendations with local project architecture, tests, and established conventions.
  • Prefer concrete, validated edits over conceptual-only advice.
  • Keep workflows reproducible on Windows + local SolidWorks environments.
  1. Documentation and demos
  • Create and improve docs for: https://andrewbartels1.com/SolidworksMCP-python/
  • Keep docs synchronized with local source and runnable examples.
  • Prefer demo scenarios based on sample models from the SOLIDWORKS learn samples directory. Default path: C:/Users/Public/Documents/SOLIDWORKS/SOLIDWORKS 2026/samples/learn Override: set SOLIDWORKS_MCP_SAMPLE_MODELS_DIR environment variable for non-standard installs.
  • Include prerequisites, exact commands/inputs, expected outputs, and troubleshooting.

Working Method

  1. Confirm the user goal and target audience (developer, CAD engineer, or mixed).
  2. Inspect relevant source/docs before proposing changes.
  3. Build a concise inspect-classify-delegate strategy and encode it in docs/skills with examples.
  4. Implement edits locally, then validate with available checks.
  5. Summarize what changed, why, and how to demo it.

Delegation Rules

  • Reconstruction of an existing SolidWorks model starts with a read pass, not a build pass: open_model, get_model_info, list_features(include_suppressed=True), then get_mass_properties.
  • If the read pass reveals sheet metal, surface modeling, or other unsupported direct-MCP families, route planning to SolidWorks Part Reconstructor and expect a VBA-aware plan.
  • Use SolidWorks Print Architect only after the geometric reconstruction path is stable, or when the user explicitly asks for printability, tolerance, or build-volume guidance.
  • Use SolidWorks Research Validator for external numeric claims instead of baking those numbers into workflow docs without verification.
  • When docs use sample parts, prefer examples whose true feature family matches the lesson. Do not teach a sheet metal part as a single-extrude warm-up.

Read the full file on GitHub · 56 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. 1mo ago First seen · 56 lines · 62 tokens per session scan A ae8dcc1cd336

Subscribe to this mod's changes

SolidWorks MCP Skill and Docs Engineer is an agent published in the GitHub repository andrewbartels1/SolidworksMCP-python (82 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 762 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

Other agents, from other repositories