FastVideo: Skill for Claude Code

.agents/skills/add-model-03-port-dit/SKILL.md

add-model-03-port-dit is a skill for Claude Code, Codex from hao-ai-lab/FastVideo. It costs 36 tokens per session (1,074 once invoked), scanned A, original, Apache-2.0.

A focused workflow for prototyping or checking one DiT, or diffusion transformer, component in FastVideo. Diffusion transformers are neural-network components commonly used in systems that generate or transform video.

In plain words
What is it for?
Use it during the specified add-model phases with the required test, weights, and target files to implement or compare one FastVideo-native DiT component.
Why use it?
It limits model-porting work to one transformer component, helping identify mismatched shapes, unsupported layers, configuration differences, and other parity problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is hao-ai-lab/FastVideo's own configuration. It tells Claude Code and Codex how to work on FastVideo 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 FastVideo configures →

About the project

FastVideo is a framework for training and running accelerated video-generation models, including real-time inference and post-training workflows. It is for researchers and developers building or deploying diffusion-based systems that generate video.

hao-ai-lab/FastVideo · 4,368 stars · on GitHub · hao-ai-lab.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to hao-ai-lab/FastVideo. 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/hao-ai-lab/FastVideo/main/.agents/skills/add-model-03-port-dit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hao-ai-lab/FastVideo

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 add-model-03-port-dit

README.md
[![agentmods](https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-03-port-dit/github.svg)](https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-03-port-dit)
Your own site
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-03-port-dit"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-03-port-dit/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 add-model-03-port-dit

Your own site · 80×15
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-03-port-dit"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-03-port-dit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,074 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 $0.00036 $0.01074
Opus 5 $0.00018 $0.00537
Sonnet 5 $0.00007 $0.00215
Haiku 4.5 $0.00004 $0.00107

Measured 12d ago against content hash 08308dd144e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

add-model-03-port-dit 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 12d 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.

.agents/skills/add-model-03-port-dit/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Model Port DiT

Goal

Prototype or parity-debug one diffusion transformer in FastVideo-native code. This skill is for one component only; do not work on the VAE, encoders, pipeline, or unrelated conversion code unless the current component cannot load without a minimal fix there.

Inputs

Follow ../add-model/shared/component_skill_common.md and require the complete packet from ../add-model/contracts/component_context.md.

DiT-specific packet fields:

  • component: transformer or DiT name.
  • parity_test: tests/local_tests/<bucket>/test_<family>_<component>_parity.py.
  • weights: converted transformer dir or local official path.
  • target_files: fastvideo/models/dits/<family>.py and fastvideo/configs/models/dits/<family>.py.

Modes

Use the common prototype and parity-debug modes from ../add-model/shared/component_skill_common.md.

DiT-specific prototype concerns include ambiguous official flags, shape mismatches, missing FastVideo layer equivalents, and dedicated output heads.

Reuse Proof

Apply the shared reuse proof. DiT-specific comparison must include attention algorithm, positional embeddings, RoPE/patching, timestep/guidance embeddings, scaling constants, dtype casts, state-dict names, and every output head.

Existing FastVideo Patterns

  • Base class: fastvideo/models/dits/base.py::BaseDiT.
  • Config bases: DiTConfig and DiTArchConfig in fastvideo/configs/models/dits/base.py.
  • Use the matching DiT config bucket. Wrong bucket inheritance can typecheck but fail during pipeline wiring.
  • Config export: add the config to fastvideo/configs/models/dits/__init__.py.
  • Registry discovery: set EntryClass = <ClassName> in the model file.
  • Loader path: TransformerLoader reads transformer/config.json, calls dit_config.update_model_arch(config), resolves _class_name through ModelRegistry, and constructs the class with config and hf_config.
  • Reference examples: stable_audio.py, wanvideo.py, sd3.py, longcat.py, and ltx2.py.
  • Layer guidance: fastvideo/layers/AGENTS.md.

Read the full file on GitHub · 115 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. 12d ago First seen · 115 lines · 36 tokens per session scan A 08308dd144e2

Subscribe to this mod's changes

add-model-03-port-dit is a skill published in the GitHub repository hao-ai-lab/FastVideo (4,368 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,074 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 2026-08-30.