freecad-mcp-pro: Skill for Claude Code

.opencode/skills/f-code-review/SKILL.md

f-code-review is a skill for Claude Code, OpenCode from GadatheGod/freecad-mcp-pro. It costs 35 tokens per session (558 once invoked), scanned A, original, MIT.

A review workflow for changes made through FreeCAD MCP, the interface used to create or modify FreeCAD models. It checks both technical correctness and whether the result matches the design or ticket.

In plain words
What is it for?
Use it to review FreeCAD geometry, finite-element setups, or assemblies against FreeCAD documentation and a supplied design specification.
Why use it?
It catches incorrect FreeCAD object types or properties as well as geometry that does not match the requested specification.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: disable-model-invocation in frontmatter, but also installed under .opencode/. Also seen: mentions subagents; mentions OpenCode.

This is GadatheGod/freecad-mcp-pro's own configuration. It tells Claude Code and OpenCode how to work on freecad-mcp-pro 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 freecad-mcp-pro configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/praveen/Desktop/Freecadmcp/docs/freecad/.

Reuse

Borrowing it

Nothing to install: this file belongs to GadatheGod/freecad-mcp-pro. 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/GadatheGod/freecad-mcp-pro/main/.opencode/skills/f-code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GadatheGod/freecad-mcp-pro

Made for: Claude Code, OpenCode.

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 f-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/gadathegod/freecad-mcp-pro/f-code-review/github.svg)](https://agentmods.dev/skills/gadathegod/freecad-mcp-pro/f-code-review)
Your own site
<a href="https://agentmods.dev/skills/gadathegod/freecad-mcp-pro/f-code-review"><img src="https://agentmods.dev/badge/skills/gadathegod/freecad-mcp-pro/f-code-review/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 f-code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/gadathegod/freecad-mcp-pro/f-code-review"><img src="https://agentmods.dev/badge/skills/gadathegod/freecad-mcp-pro/f-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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 $0.00035 $0.00558
Opus 5 $0.00017 $0.00279
Sonnet 5 $0.00007 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 10d ago against content hash 842fd7327328, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

f-code-review 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 10d 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.

.opencode/skills/f-code-review/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review — FreeCAD Edition

Review FreeCAD geometry creation, FEM setup, or assembly changes along two axes:

  • Standards — Do objects use correct types/properties per FreeCAD documentation?
  • Spec — Does the geometry match the design spec or ticket?

Context

  • FreeCAD docs: /home/praveen/Desktop/Freecadmcp/docs/freecad/
  • Object reference: /home/praveen/Desktop/Freecadmcp/.opencode/skills/freecad-objects/
  • Spec/ticket: Provided by user or found in .scratch/

Process

1. Identify what was changed

Get the list of FreeCAD objects created/modified:

get_objects(doc_name="ProjectName")

2. Standards Review (parallel sub-agent)

Check against FreeCAD documentation:

Object Type Standards:

  • Part::Box uses Length/Width/Height (not XSize/YSize/ZSize)
  • Part::Cylinder uses Radius/Height (not Diameter)
  • Part::Cone uses Radius/Radius2/Height
  • Part::Torus uses Radius/MainRadius/MinorRadius
  • Draft::Circle uses Radius (not Diameter)
  • ViewObject.ShapeColor is [R,G,B,Alpha] with 0-1 range
  • Placement.Base uses {x,y,z} not {X,Y,Z}

FEM Standards:

  • ConstraintFixed references valid faces
  • ConstraintForce references valid faces with correct direction
  • FemMeshGmsh references valid shape
  • CharacteristicLengthMax/Min are reasonable for part size

Common Errors to Flag:

  • Wrong property names (e.g., "Diameter" instead of "Radius")
  • Invalid face references (Face1 vs Face.1)
  • Missing required properties
  • Incorrect data types (string vs number)

3. Spec Review (parallel sub-agent)

Check against the design spec:

  • All dimensions match spec values
  • All features are present (holes, fillets, chamfers)
  • Material properties match spec
  • FEM constraints match spec (location, magnitude)
  • Assembly hierarchy matches spec

4. Aggregate

Present findings under ## Standards and ## Spec:

Standards findings:

  • Object type errors
  • Property name/value errors
  • FEM constraint errors

Spec findings:

  • Missing features
  • Dimension mismatches
  • Missing constraints

Read the full file on GitHub · 78 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. 10d ago First seen · 78 lines · 35 tokens per session scan A 842fd7327328

Subscribe to this mod's changes

f-code-review is a skill published in the GitHub repository GadatheGod/freecad-mcp-pro (1 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 558 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 2026-08-31.