hf-architecture-tikz

hf-architecture-tikz is a skill for Claude Code, Codex from yzlnew/infra-skills. It costs 142 tokens per session (2,178 once invoked), scanned A, original, no licence file.

A guide for drawing detailed diagrams of decoder-only language models from Hugging Face, a platform that hosts machine-learning models. The diagrams can show model blocks, parameter formulas, and concrete values.

In plain words
What is it for?
Use it to diagram models with attention variants such as MHA, GQA, and MLA, as well as dense or mixture-of-experts feed-forward layers and related components.
Why use it?
It helps explain how different language-model architectures are built and how their parameter counts are calculated.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to diagram models with attention variants such as MHA, GQA, and MLA, as well as dense or mixture-of-experts feed-forward layers and related components.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yzlnew/infra-skills/hf-architecture-tikz
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 yzlnew/infra-skills --skill hf-architecture-tikz
Clone the repo
git clone --depth 1 https://github.com/yzlnew/infra-skills

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 hf-architecture-tikz

README.md
[![agentmods](https://agentmods.dev/badge/skills/yzlnew/infra-skills/hf-architecture-tikz/github.svg)](https://agentmods.dev/skills/yzlnew/infra-skills/hf-architecture-tikz)
Your own site
<a href="https://agentmods.dev/skills/yzlnew/infra-skills/hf-architecture-tikz"><img src="https://agentmods.dev/badge/skills/yzlnew/infra-skills/hf-architecture-tikz/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 hf-architecture-tikz

Your own site · 80×15
<a href="https://agentmods.dev/skills/yzlnew/infra-skills/hf-architecture-tikz"><img src="https://agentmods.dev/badge/skills/yzlnew/infra-skills/hf-architecture-tikz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,178 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 unknown 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 $0.00142 $0.02178
Opus 5 $0.00071 $0.01089
Sonnet 5 $0.00028 $0.00436
Haiku 4.5 $0.00014 $0.00218

Measured 13d ago against content hash 09b85d7a20bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hf-architecture-tikz 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 13d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/compile.sh, scripts/extract_arch.py, scripts/render_tikz.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

hf-architecture-tikz/SKILL.md · 97 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 13d ago First seen · 97 lines · 142 tokens per session scan A 09b85d7a20bb

Subscribe to this mod's changes

hf-architecture-tikz is a skill published in the GitHub repository yzlnew/infra-skills (146 stars, last pushed 2mo ago), with no licence file. It adds 142 tokens to every session and 2,178 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

cvqnn

Skill for understanding, using, and implementing the Continuous Variable Quantum Neural Network (CVQNN) for binary classification via the CVQNNAlgorithm class, CVSimulator, and CVClassifier. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.

unitarylab/quantum-practices · 61 tokens

vqc

Skill for understanding, using, and implementing the Variational Quantum Classifier (VQC) for Iris dataset classification with data re-uploading and Parameter Shift Rule via the VQCAlgorithm class. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.

unitarylab/quantum-practices · 61 tokens

pennylane

PennyLane - A versatile quantum machine learning library that supports hybrid quantum-classical computations.

unitarylab/quantum-practices · 23 tokens

quantum-machine-learning

Variational quantum algorithms for optimization and machine learning, including QAOA for combinatorial optimization, VQE for ground-state energy estimation, Fermi-Hubbard VQE for lattice models, VQC for supervised learning, QCBM for generative modeling, and CVQNN for continuous-variable workflows. Skill-first for…

unitarylab/quantum-practices · 86 tokens

iterate-ml-experiment

Owns the iteration loop on top of an ML workspace: the journal/JOURNAL.md index and the per-experiment journal/NNshortname.md design notes that must be drafted and approved by the user before experiments/NNshortname.py is created. Drives the propose → iterate → approve → implement → record loop; dispatches to…

probabl-ai/skills · 422 tokens

iterate-from-user

Source the next ML experiment proposal from the user via one of three entry points selected by AskUserQuestion: (a) a scientific article URL the agent must read and synthesize, (b) a resource link or path (GitHub issue / spec file / reference repo), or (c) free-text the user types directly. In every branch, the agent…

probabl-ai/skills · 401 tokens