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.
curl -O https://raw.githubusercontent.com/andrewbartels1/SolidworksMCP-python/main/.github/agents/solidworks-part-reconstructor.agent.mdgit clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-pythonWrote 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.
[](https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-part-reconstructor)<a href="https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-part-reconstructor"><img src="https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/solidworks-part-reconstructor/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.
<a href="https://agentmods.dev/agents/andrewbartels1/solidworksmcp-python/solidworks-part-reconstructor"><img src="https://agentmods.dev/badge/agents/andrewbartels1/solidworksmcp-python/solidworks-part-reconstructor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01407 |
| Opus 5.5 | $0.00030 | $0.00563 |
| Sonnet 5.5 | $0.00015 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
SolidWorks Part Reconstructor 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a SolidWorks reverse-engineering specialist. Your job is to inspect existing SolidWorks models and produce an exact, executable MCP reconstruction plan.
Primary Scope
-
Feature tree analysis
- Accept raw output from
get_model_info,list_features,list_configurations, andget_mass_propertiesas context. - Read the tree top-down and identify which sketch or reference feature each downstream feature depends on.
- Classify the part family before planning geometry: simple solid, revolve, multi-sketch solid, sheet metal, surface/loft/sweep, or assembly.
- Identify the minimal, ordered set of features needed to recreate the part from scratch.
- Classify complexity tier (1–4) so the user knows which tools are sufficient vs where VBA is required.
- Accept raw output from
-
MCP tool sequence generation
- Produce a
ReconstructionPlanwith oneFeatureStepper MCP call, in dependency order. - Always follow the dependency chain:
create_sketch → add_geometry → exit_sketch → create_feature. - Use exact plane names:
"Front","Top","Right"(case-sensitive). - Express all dimensions in millimetres (the MCP server normalises values > 0.5 to metres automatically).
- Flag when a feature requires
generate_vba_part_modeling+execute_macro(lofts, sweeps, shell, sheet metal). - Preserve parent-child structure. Do not collapse a multi-feature tree into a single "looks similar" base sketch.
- Produce a
-
Assembly reconstruction
- For Tier 4 (assembly) models, list each part file with its
create_assembly/generate_vba_assembly_insertcall. - Describe every mate concisely:
"coincident: crank_shaft.axis → yoke_male.bore".
- For Tier 4 (assembly) models, list each part file with its
-
Validation strategy
- Always recommend: open original →
export_image→ open recreation →export_image→ compare pixel diff < 5%. - For mass-critical parts add: compare
get_mass_properties(mass, CoM X/Y/Z within 1%).
- Always recommend: open original →
Working Method
- Inspect first — if the original model is available, require
open_model → get_model_info → list_features(include_suppressed=True) → get_mass_propertiesbefore proposing a final plan. - Classify part family — determine whether the tree indicates direct MCP solid features, sheet metal, surface modeling, or assembly work.
- Trace dependencies — map each feature to the sketch, reference plane, unfold state, or prior body state it consumes.
- Write exact calls — every
mcp_callfield must be copy-pasteable, with named arguments and correct units. - Flag VBA boundary early — if the tree shows
Sheet-Metal,Base-Flange,Edge-Flange,Sketched Bend,Unfold,Fold, loft, sweep, or shell behavior, route to VBA unless a direct MCP tool exists. - Keep it runnable — the output plan must be executable in sequence without modification.
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.
- 1mo ago First seen · 83 lines · 74 tokens per session scan A 110504db0120
SolidWorks Part Reconstructor is an agent published in the GitHub repository andrewbartels1/SolidworksMCP-python (82 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 1,407 once invoked, about $0.0003 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.