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.
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.
curl -O https://raw.githubusercontent.com/hao-ai-lab/FastVideo/main/.agents/skills/add-model-08-trace/SKILL.mdgit clone --depth 1 https://github.com/hao-ai-lab/FastVideoWrote 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.
[](https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-08-trace)<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-08-trace"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-08-trace/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.
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/add-model-08-trace"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/add-model-08-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.02119 |
| Opus 5 | $0.00026 | $0.01059 |
| Sonnet 5 | $0.00010 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
add-model-08-trace 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.
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.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add-Model Trace
Manual Invocation
Load this skill when /add-model Phase 6 component parity has failed and the
root cause requires layer-by-layer divergence analysis. This skill is not
auto-fired. The calling subagent (DiT, VAE, encoder, or generic port skill)
loads it when its standard parity-debug loop hits a wall and cannot isolate
the divergence from end-to-end tensor comparisons alone.
Do not load this skill for first-pass parity failures. Try weight-diff and end-to-end tensor comparison first. Load this skill only when those do not isolate the cause.
Goal
Find the first numerical divergence point between FastVideo's port and the official reference, layer by layer, by instrumenting both sides at matching tensor boundaries. The investigation must leave zero source residue in production code when it closes.
When To Run
After a component parity test FAILS at a bf16-noise-realistic tolerance AND the calling subagent's first-pass debug (weight-diff, end-to-end tensor compare) does not isolate the cause.
Required inputs before starting:
- A working FastVideo loader for the component under investigation.
- A working official loader, typically via
tests/local_tests/helpers/<family>_upstream.py::load_upstream_<component>. - Shared deterministic test inputs (same tensors on both sides).
- The component parity test file path and its current failure output.
Primary Path: FastVideo Activation Trace
Use FastVideo's first-class activation trace before writing custom hooks:
fastvideo/hooks/activation_trace.py, documented in
docs/contributing/activation_trace.md.
Pipeline runs attach trace to the transformer during pipeline initialization.
Component-only parity harnesses may call attach_activation_trace(model) from
local test/debug code; do not add trace calls to production model code.
Prefix the failing parity command with a tight layer regex:
FASTVIDEO_TRACE_ACTIVATIONS=1 \
FASTVIDEO_TRACE_LAYERS="^block\.layers\.[0-9]+$" \
FASTVIDEO_TRACE_STATS="abs_mean,sum,max,shape" \
FASTVIDEO_TRACE_STEPS="0" \
FASTVIDEO_TRACE_OUTPUT="/tmp/opencode/fv_trace.jsonl" \
pytest tests/local_tests -k "parity" -v -s
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.
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.
- 10d ago First seen · 215 lines · 52 tokens per session scan A d6c0c2912278
add-model-08-trace is a skill published in the GitHub repository hao-ai-lab/FastVideo (4,363 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,119 once invoked, about $0.0003 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.
Other skills, from other repositories
diffusers-ascend-pipeline
A guide for running image and video generation pipelines on Huawei Ascend NPUs with the Diffusers library. Diffusers is a software library for using generative models, and the guide covers model pipelines, memory settings, LoRA adapters, and multi-card inference.
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
relax-dev-debug
Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.
pr-babysitter
Use when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.
debug-hang
A troubleshooting workflow for Ray, a system that runs machine-learning jobs across multiple computers or GPUs, when a distributed training job stops making progress.
submit-github-bug-issue
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…