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.
npx agentmods add skills/just1step/solidworks-mcp/solidworksmodelingnpx skills add just1step/solidworks-mcp --skill solidworksmodelinggit clone --depth 1 https://github.com/just1step/solidworks-mcpWrote 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/skills/just1step/solidworks-mcp/solidworksmodeling)<a href="https://agentmods.dev/skills/just1step/solidworks-mcp/solidworksmodeling"><img src="https://agentmods.dev/badge/skills/just1step/solidworks-mcp/solidworksmodeling.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.02512 |
| Opus 5 | $0.00023 | $0.01256 |
| Sonnet 5 | $0.00009 | $0.00502 |
| Haiku 4.5 | $0.00005 | $0.00251 |
Grade A, and why
solidworksmodeling 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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SolidWorks Modeling Skill
Use this skill when the task involves editing a SolidWorks part or assembly through MCP tools, especially for interference fixes, topology-driven selection, sketch-based feature work, or assembly verification.
Core Rules
- Confirm the active document first. Do not assume the visible window is the part you intend to edit.
- Opening a document is not the same as activating it. If a document is already open, explicitly confirm that it became the active document before reading components, replacing parts, or editing geometry.
- Treat SolidWorks as a selection-first UI. Use the FeatureManager tree to identify the real target object, then use commands or MCP tools against that confirmed target.
- For assembly interference issues, identify the actual component file paths before changing geometry.
- In large or nested assemblies, do not stop at the top-level component list. Prefer
ListComponentsRecursiveto locate the concrete part file that owns the interfering geometry. - Before any sketch-based operation, clear the current selection, select a real planar face on the target solid, and only then start the sketch.
- Do not create sketches in free space when the intent is to modify model geometry. Face-hosted sketches are materially more stable.
- When reasoning about SolidWorks APIs, prefer official API names and official preconditions. Do not invent wrapper-style method names and then reason from those invented semantics.
- Before reading the FeatureManager tree or deleting features or loose sketches, call
GetEditStatefirst. IfIsEditingis true, finish the active sketch beforeListFeatureTree,DeleteFeatureByName, orDeleteUnusedSketches. - If a face-based cut or boss fails, verify the feature direction. A top-face relief cut often needs the direction flipped so the feature goes into the body.
- In localized SolidWorks environments, do not rely on English plane labels. Prefer semantic plane resolution or topology-driven selection.
- If the target part is reused in the assembly, first determine how many instances reference that same part file and explicitly tell the user which other placements will also change before editing the geometry.
- If only one reused placement needs to change, prefer replacing that single instance with a separate part file instead of editing the shared source part.
ReplaceComponents2only replaces top-level components in the active assembly. For nested content, open the owning subassembly, activate it, replace the child there, save, then return to the parent assembly for verification.- Preserve functional geometry unless the user explicitly requests otherwise. For pulley brackets, keep pulley hole size and pulley center position unchanged while adjusting only clearance material.
- Prefer the smallest edit that removes the issue, such as a shallow relief cut or reducing a non-functional top surface.
- Treat extrude, cut, revolve, shell, and other shape-changing feature edits as high-risk operations. After each such edit, export and inspect at least front, top, and right views before trusting the result.
- Never rely on a single view after a high-risk geometry edit. If the shape still looks ambiguous, also inspect an isometric view.
- If the three-view check shows an unexpected silhouette, floating geometry, or any unclear result, stop and show the views to the user before continuing with more edits.
- Save the edited part before reopening or checking the parent assembly.
- After saving, verify the result in the assembly and confirm there is visible clearance rather than coplanar overlap.
- After any replacement-based fix, rerun a directed interference check against the intended target pair. An alternate part name or file does not prove that clearance now exists.
- When named selection is unreliable, inspect topology first and select faces or edges by index.
- If document or assembly queries suddenly start failing with
0x800706BA, assume the cached COM session may be stale and verify Hub health before editing geometry.
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.
- 6d ago First seen · 142 lines · 47 tokens per session scan A 434721d1bba7
solidworksmodeling is a skill published in the GitHub repository just1step/solidworks-mcp (22 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 2,512 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 2026-08-30.
Other skills, from other repositories
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…