SolidworksMCP-python: Command for GitHub Copilot

.github/prompts/feature-tree-reconstruction.prompt.md

feature-tree-reconstruction is a command for GitHub Copilot from andrewbartels1/SolidworksMCP-python. It costs 35 tokens per session (422 once invoked), scanned A, original, MIT.

Classify an existing SolidWorks model from its real feature tree before planning reconstruction. Use when recreating from an existing part, screenshot, mock-up drawing, or sample model.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is andrewbartels1/SolidworksMCP-python's own configuration. It tells GitHub Copilot 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/prompts/feature-tree-reconstruction.prompt.md
Clone the repo
git clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-python

Made for: GitHub Copilot.

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 feature-tree-reconstruction

README.md
[![agentmods](https://agentmods.dev/badge/commands/andrewbartels1/solidworksmcp-python/feature-tree-reconstruction.svg)](https://agentmods.dev/commands/andrewbartels1/solidworksmcp-python/feature-tree-reconstruction)
Your own site
<a href="https://agentmods.dev/commands/andrewbartels1/solidworksmcp-python/feature-tree-reconstruction"><img src="https://agentmods.dev/badge/commands/andrewbartels1/solidworksmcp-python/feature-tree-reconstruction.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00035 $0.00422
Opus 5 $0.00017 $0.00211
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured today against content hash f88ec20eb774, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feature-tree-reconstruction 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 today.

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/prompts/feature-tree-reconstruction.prompt.md · 39 lines

What it actually says

Run an inspect-classify-delegate pass before planning any reconstruction.

Inputs:

  • Target model path: ${input:modelPath:C:/Users/Public/Documents/SOLIDWORKS/SOLIDWORKS 2026/samples/learn/Baseball Bat.SLDPRT}
  • User goal: ${input:userGoal:Reconstruct the model faithfully and identify the right MCP vs VBA workflow}
  • Extra context: ${input:extraContext:Optional screenshot notes, constraints, or dimensions}

Required workflow:

  1. If a model path is provided, open the original file first.
  2. Read the active state with:
    • get_model_info()
    • list_features(include_suppressed=True)
    • get_mass_properties()
    • classify_feature_tree()
  3. Summarize the part family, confidence, evidence, and any warnings.
  4. Trace the likely parent-child dependency chain from the feature tree.
  5. Decide whether the path is:
    • direct MCP solid modeling
    • VBA-backed advanced part modeling
    • assembly planning
    • drawing workflow
    • insufficient evidence, inspect more
  6. Only then propose the next reconstruction steps.

Output requirements:

  • Start with Classification Summary
  • Then Why This Classification
  • Then Recommended Workflow
  • Then Next Concrete Steps
  • If confidence is low, say what additional evidence is needed before building

Rules:

  • Do not infer “simple extrude” from silhouette alone if the original file is available.
  • If the tree shows sheet metal markers (Sheet-Metal, Base-Flange, Edge-Flange, Sketched Bend, Unfold, Fold), preserve that family in the recommendation.
  • If only sketch/profile features are visible, treat the result as provisional and combine it with mass properties and images before committing to a rebuild path.
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. today First seen · 39 lines · 35 tokens per session scan A f88ec20eb774

Subscribe to this mod's changes

feature-tree-reconstruction is a command published in the GitHub repository andrewbartels1/SolidworksMCP-python (70 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 422 once invoked, about $0.0002 per session on Opus 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 2026-09-06.