mesh-inspect

mesh-inspect is a skill for Claude Code from kimimgo/viznoir. It costs 97 tokens per session (386 once invoked), scanned A, original, MIT.

A tool for checking, measuring and converting 3D mesh files. A mesh is a surface made from connected points and faces, commonly used to represent objects in 3D software.

In plain words
What is it for?
It helps inspect STL, OBJ, PLY and other mesh files, check watertightness and geometry quality, report mesh statistics, and convert between formats such as STL, VTU, MSH, INP, CGNS and EXO.
Why use it?
It finds structural problems that can make a mesh unusable, such as holes, inconsistent face directions or zero-area faces. It also avoids needing separate conversion tools for each file format.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the viznoir plugin — 9 skills, 1 command, 3 agents, 1 MCP server shipped together

Good fit It helps inspect STL, OBJ, PLY and other mesh files, check watertightness and geometry quality, report mesh statistics, and convert between formats such as STL, VTU, MSH, INP, CGNS and EXO.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimimgo/viznoir/mesh-inspect
Install

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.

Any agent
npx skills add kimimgo/viznoir --skill mesh-inspect
Clone the repo
git clone --depth 1 https://github.com/kimimgo/viznoir

Made for: Claude Code.

Or install viznoir, the plugin that ships this one along with the rest of its 9 skills, 1 command, 3 agents, 1 MCP server.

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 mesh-inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimimgo/viznoir/mesh-inspect/github.svg)](https://agentmods.dev/skills/kimimgo/viznoir/mesh-inspect)
Your own site
<a href="https://agentmods.dev/skills/kimimgo/viznoir/mesh-inspect"><img src="https://agentmods.dev/badge/skills/kimimgo/viznoir/mesh-inspect/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 mesh-inspect

Your own site · 80×15
<a href="https://agentmods.dev/skills/kimimgo/viznoir/mesh-inspect"><img src="https://agentmods.dev/badge/skills/kimimgo/viznoir/mesh-inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00097 $0.00386
Opus 5 $0.00048 $0.00193
Sonnet 5 $0.00019 $0.00077
Haiku 4.5 $0.00010 $0.00039

Measured 10d ago against content hash 2339c6fa4a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mesh-inspect 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.

skills/mesh-inspect/SKILL.md · 50 lines

What it actually says

Mesh Inspection Skill

You are a mesh/geometry analysis expert. When the user wants to inspect or process mesh files, follow this workflow:

Step 1: Identify Files

Find mesh files: .stl, .obj, .ply, .msh, .inp, .cgns, .exo, .vtu

Step 2: Analysis

Use appropriate MCP tools or Python libraries:

Quality Checks

  • Manifold: Is the mesh watertight? Any non-manifold edges?
  • Normals: Consistent face normals? Any inverted faces?
  • Degenerates: Zero-area faces? Duplicate vertices?
  • Bounds: Bounding box dimensions, center of mass

Format Conversion

Use meshio for 50+ format conversions:

.stl ↔ .vtu ↔ .msh ↔ .inp ↔ .cgns ↔ .exo

Mesh Statistics

  • Face count, vertex count, edge count
  • Min/max/avg edge length
  • Aspect ratio distribution
  • Volume (if closed)

Step 3: Report

Present results with:

  1. Pass/fail for each quality metric
  2. Specific locations of issues (if any)
  3. Suggested fixes
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 · 50 lines · 97 tokens per session scan A 2339c6fa4a2f

Subscribe to this mod's changes

mesh-inspect is a skill published in the GitHub repository kimimgo/viznoir (18 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 386 once invoked, about $0.0005 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.