FastVideo: Skill for Claude Code

.agents/skills/add-model-07-conversion/SKILL.md

add-model-07-conversion is a skill for Claude Code, Codex from hao-ai-lab/FastVideo. It costs 39 tokens per session (1,884 once invoked), scanned A, original, Apache-2.0.

A checkpoint conversion workflow for turning a model's official weight files into the component-based layout expected by FastVideo, a video-generation system. It writes the conversion script, output files, configuration, and load checks.

In plain words
What is it for?
Use it to convert a model family’s weights, create per-component folders and model_index.json, preserve required extra files, and verify loading with strict checks.
Why use it?
It removes the need to manually map model parameters, split weights, and check whether FastVideo can load the result. It also records the conversion state and retry history.

Skill for Claude CodeCodex

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

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 · 4,363 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-07-conversion/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-07-conversion

README.md
[![agentmods](https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-07-conversion/github.svg)](https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-07-conversion)
Your own site
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-07-conversion"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-07-conversion/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-07-conversion

Your own site · 80×15
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-07-conversion"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-07-conversion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,884 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 $0.00039 $0.01884
Opus 5 $0.00019 $0.00942
Sonnet 5 $0.00008 $0.00377
Haiku 4.5 $0.00004 $0.00188

Measured 10d ago against content hash e5f0c5e600dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-model-07-conversion 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.

The scan reads SKILL.md. This mod also ships 1 executable file (templates/family_to_diffusers.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.

.agents/skills/add-model-07-conversion/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Model Conversion

Goal

Convert official weights into a FastVideo-loadable component layout after Phase 4 native prototypes exist. The conversion script owns parameter mapping, component splitting, passthrough assets, config emission, and strict-load verification.

Inputs

Follow ../add-model/shared/common_rules.md for token/auth safety, state files, escape hatches, production boundaries, and skip/pass semantics.

Require the initial request from ../add-model/contracts/conversion_request.md.

If the FastVideo key/shape dump is missing, return to /add-model Phase 4. Do not write a final mapping against an unimplemented component.

For Phase 6 retry requests from component skills, also require the retry shape from ../add-model/contracts/conversion_request.md.

Output

  • scripts/checkpoint_conversion/<family>_to_diffusers.py.
  • converted_weights/<family>/ with model_index.json and per-component subfolders.
  • Updated tests/local_tests/<model_family>/README.md with conversion command, source layout, output path, and strict-load status.
  • Updated tests/local_tests/<model_family>/PORT_STATUS.md with conversion state, retry history, open questions, and issues/blockers.

Reference Scripts

  • scripts/checkpoint_conversion/convert_ltx2_weights.py: component prefix splitting, metadata config extraction, passthrough Gemma/tokenizer assets, and optional component-only output.
  • scripts/checkpoint_conversion/stable_audio_to_diffusers.py: monolithic model.safetensors split into transformer/VAE/conditioner, plus copied passthrough subfolders. Use this shape for single-checkpoint official repos.
  • scripts/checkpoint_conversion/convert_gamecraft_full.py: separate official sources for transformer, VAE, text encoders, tokenizers, scheduler, and root model_index.json.
  • scripts/checkpoint_conversion/longcat_to_fastvideo.py: fused QKV/KV split, renamed native transformer weights, and copied existing Diffusers components.
  • scripts/checkpoint_conversion/pt_to_safetensors.py: simple .pt extraction helper for nested checkpoint dictionaries.

Read the full file on GitHub · 187 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 187 lines · 39 tokens per session scan A e5f0c5e600dc

Subscribe to this mod's changes

add-model-07-conversion is a skill published in the GitHub repository hao-ai-lab/FastVideo (4,363 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,884 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.