llm_3d

llm_3d is a skill for Claude Code, Codex from antoinebou12/uml-mcp. It costs 92 tokens per session (701 once invoked), scanned A, original, MIT.

A format guide for describing a neural network or large language model as a rotatable 3D scene. It produces the JSON used by the uml-mcp diagram tool and its visualizer.

In plain words
What is it for?
Use it to show model layers, repeated blocks, groups and connections as an interactive HTML scene or a static SVG image.
Why use it?
It avoids having to learn the exact data format for layered model diagrams. Validation can catch format errors before the diagram is generated.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to show model layers, repeated blocks, groups and connections as an interactive HTML scene or a static SVG image.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/antoinebou12/uml-mcp/llm_3d
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 antoinebou12/uml-mcp --skill llm_3d
Clone the repo
git clone --depth 1 https://github.com/antoinebou12/uml-mcp

Made for: Claude Code, Codex.

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 llm_3d

README.md
[![agentmods](https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/llm_3d/github.svg)](https://agentmods.dev/skills/antoinebou12/uml-mcp/llm_3d)
Your own site
<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/llm_3d"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/llm_3d/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 llm_3d

Your own site · 80×15
<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/llm_3d"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/llm_3d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 701 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 $0.00092 $0.00701
Opus 5.5 $0.00037 $0.00280
Sonnet 5.5 $0.00018 $0.00140
Haiku 4.5 $0.00009 $0.00070

Measured yesterday against content hash 19c6721cea57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm_3d 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 yesterday.

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.

.skill/skills/llm_3d/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llm_3d diagram (uml-mcp plugin llm-visualizer)

diagram_type: llm_3d
Backend: plugin:llm-visualizer (bundled with uml-mcp, on by default)
Output formats: html, svg

LLM architecture as a rotatable perspective scene. JSON layers and connections; standalone interactive HTML or static isometric SVG

Load the workflow skill uml-mcp-diagrams and the focused guide skill://uml-mcp-guides/llm-visualizer/SKILL.md. This file is notation only; it does not add an MCP tool.

Example prompt

Show the VAE as a 3D scene I can rotate, encoder narrowing to the latent and decoder widening back.

Notation tips

  • Same JSON as llm_2d; the page switches between 2D and 3D.
  • encoder and decoder layers become frustums that narrow and widen along the flow; other kinds are glass panels, repeat stacks them and groups become tinted slabs on the floor.
  • The static SVG/PNG is an oblique view with every label on one row under the solids.

Styling

Pass theme (auto, dark or light) to generate_uml / generate_uml_image, or set it in the source. auto follows the reader's system in the HTML page and is dark in static SVG and PNG.

Example source

{"title":"Decoder-only transformer","subtitle":"Grouped view of a 7B parameter language model","theme":"dark","layers":[{"id":"tokens","label":"Token IDs","kind":"input","shape":[2048],"note":"BPE token sequence"},{"id":"embed","label":"Token embedding","kind":"embedding","shape":[2048,4096]},{"id":"attn","label":"Grouped-query attention","kind":"attention","shape":[32,128],"repeat":32,"note":"32 query heads, 8 key/value heads"},{"id":"ffn","label":"SwiGLU feed-forward","kind":"feedforward","shape":[4096,11008],"repeat":32},{"id":"norm","label":"RMSNorm","kind":"normalization","shape":[4096]},{"id":"logits","label":"Vocabulary logits","kind":"output","shape":[32000]}],"connections":[{"from":"tokens","to":"embed"},{"from":"embed","to":"attn","label":"hidden states"},{"from":"attn","to":"ffn","label":"residual stream"},{"from":"ffn","to":"norm"},{"from":"norm","to":"logits"},{"from":"embed","to":"norm","label":"residual path","style":"dashed"}]}

Read the full file on GitHub · 36 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. yesterday Changed · +1 lines · +5 tokens per session 19c6721cea57
  2. 2d ago First seen · 35 lines · 87 tokens per session scan A 6ee9357bb175

Subscribe to this mod's changes

llm_3d is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 701 once invoked, about $0.0004 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 2026-11-05.

Related

llm_3d compared with skills from other repositories

llm_3d next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm_3dantoinebou12/uml-mcpSkill109yesterdayMITA92Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code