GLB authoring standards

GLB authoring standards is a skill for Claude Code from akaieuan/Hologram. It costs 86 tokens per session (997 once invoked), scanned A, original, MIT.

A set of rules for how 3D models in GLB files should be named, structured, positioned, and marked with attachment points. A GLB is a packaged 3D model file that other tools and game engines can read.

In plain words
What is it for?
Defining one root node, naming model parts, adding hand or weapon sockets, storing positions correctly, and checking triangle limits and other export conventions.
Why use it?
Consistent model structure prevents downstream tools from guessing which parts are meshes, collision shapes, or attachment points, and helps catch export errors early.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the hologram plugin — 10 skills, 6 hooks, 1 MCP server shipped together

Good fit Defining one root node, naming model parts, adding hand or weapon sockets, storing positions correctly, and checking triangle limits and other export conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akaieuan/hologram/glb-standards
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 akaieuan/Hologram --skill glb-standards
Clone the repo
git clone --depth 1 https://github.com/akaieuan/Hologram

Made for: Claude Code.

Or install hologram, the plugin that ships this one along with the rest of its 10 skills, 6 hooks, 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 GLB authoring standards

README.md
[![agentmods](https://agentmods.dev/badge/skills/akaieuan/hologram/glb-standards/github.svg)](https://agentmods.dev/skills/akaieuan/hologram/glb-standards)
Your own site
<a href="https://agentmods.dev/skills/akaieuan/hologram/glb-standards"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/glb-standards/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 GLB authoring standards

Your own site · 80×15
<a href="https://agentmods.dev/skills/akaieuan/hologram/glb-standards"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/glb-standards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 997 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 $0.00086 $0.00997
Opus 5 $0.00043 $0.00498
Sonnet 5 $0.00017 $0.00199
Haiku 4.5 $0.00009 $0.00100

Measured 11d ago against content hash c0599cd862ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

GLB authoring standards 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 11d 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.

hologram/plugin/skills/glb-standards/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLB authoring standards

A GLB is a contract between the DCC that exported it and every consumer downstream — engines, viewers, other assets. The contract only holds if it's written down and checked on every export. This skill is the catalog of conventions worth adopting, and how to enforce them with hologram check.

The conventions

One root. A single root node (usually an Empty carrying the asset's custom properties). Multiple roots make bone attachment, instancing, and transforms ambiguous.

Prefix naming. Pick prefixes that encode what a node is and stick to them — e.g. SK_ skinned/skeletal, SM_ static mesh, col_ collision-only geometry, slot_* gameplay attachment points. Consumers can then select by name instead of guessing by shape.

Socket empties. Attachment points are Socket_* Empties parented into the asset (grip points, mounts, muzzle, mag well). The rules that make them work:

  • Store socket positions in local space relative to the asset root — never world. Convert with asset.matrix_world.inverted() @ socket.matrix_world before persisting; don't rely on the asset sitting at the origin.
  • Reach-check grips. A support-hand socket the arm can't reach guarantees a bad pose: sum the arm chain's bone lengths (shoulder → forearm → hand) and keep socket-to-shoulder distance under ~95% of it. For two-handed items keep the primary-to-support grip span inside a sane band (≈ 0.20–0.50 m at human scale) — under it the hands collide, over it the arms twist.
  • Never move the attachment root (the socket the engine mounts the whole asset by). Moving it shifts the entire asset relative to the hand; if the asset clips, fix the hand-side socket instead.
  • Sockets moved → poses stale. Any pose authored against old socket positions must be re-baked (/hologram:pose-authoring).

Custom properties. Consumers shouldn't infer type from names alone — stamp the root with explicit extras (asset class, version, category) and export with export_extras=True.

Read the full file on GitHub · 88 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. 11d ago First seen · 88 lines · 86 tokens per session scan A c0599cd862ba

Subscribe to this mod's changes

GLB authoring standards is a skill published in the GitHub repository akaieuan/Hologram (2 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 997 once invoked, about $0.0004 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.