FastVideo: Skill for Claude Code

.agents/skills/reseed-performance-baseline/SKILL.md

reseed-performance-baseline is a skill for Claude Code, Codex from hao-ai-lab/FastVideo. It costs 162 tokens per session (6,572 once invoked), scanned A, original, Apache-2.0.

A procedure for updating FastVideo's recorded performance baseline from reviewed benchmark results. A performance baseline is the reference used to detect changes in speed, throughput, or memory use.

In plain words
What is it for?
Accepting reviewed performance JSON files and recording new baseline results for later performance checks.
Why use it?
It prevents intentional runtime, dependency, environment, or calibration changes from being treated as unexpected performance regressions.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python fastvideo/tests/performance/seed_baseline.py \.

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/reseed-performance-baseline/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 reseed-performance-baseline

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/reseed-performance-baseline"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/reseed-performance-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,572 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 623
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00162 $0.06572
Opus 5 $0.00081 $0.03286
Sonnet 5 $0.00032 $0.01314
Haiku 4.5 $0.00016 $0.00657

Measured 11d ago against content hash 3a507a63be89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reseed-performance-baseline 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 11d 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/reseed-performance-baseline/SKILL.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Re-seed Performance Baseline

Purpose

Replace or advance the rolling performance baseline in the HF dataset FastVideo/performance-tracking. Legacy targets are scoped by (model_id, gpu_type). V2 targets are scoped by exact comparable identity: workload_id, variant_id, benchmark_version, hardware_profile_id, software_profile_id, and recipe_fingerprint.

Performance comparison uses the median of up to the last 5 successful, baseline-eligible records for the same target. Failed or calibration-only records are useful audit history, but they do not move the future baseline because compare_baseline.py loads records with successful_only=True and baseline_eligible_only=True.

This skill now reseeds from a reviewed batch of one or more source performance JSONs. It uploads one new success=true record per accepted source JSON; it does not blindly replicate one measurement into 3 or 5 records. The effective reseed size is therefore dynamic and equals the number of provided, validated, internally consistent source JSONs.

For baseline shifts with existing history, if the operator provides fewer than 3 records, call out that the last-5 rolling median may not move immediately. If the operator provides 3 consistent shifted records, the rolling median usually moves immediately. If the operator provides 5 consistent shifted records, the last-5 window is effectively reset to the new runtime profile. For the first approved v2 baseline of a new exact identity, one reviewed calibration seed is enough for the next comparable run to leave CALIBRATION_NEEDED.

These records are intentional operator-approved baseline resets, not ordinary independent main-branch persistence. Mark them clearly with provenance fields so the HF history remains auditable.

Use this skill when a performance test fails for an intentional and reviewed reason, such as a torch/runtime/container upgrade that legitimately increases peak memory or changes timings. This is the performance equivalent of reseed-ssim-references: backup first, scope tightly, require explicit human approval, then upload reviewed accepted baseline records.

Read the full file on GitHub · 643 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. 11d ago First seen · 643 lines · 162 tokens per session scan A 3a507a63be89

Subscribe to this mod's changes

reseed-performance-baseline 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 162 tokens to every session and 6,572 once invoked, about $0.0008 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

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.

ascend-ai-coding/awesome-ascend-skills · 134 tokens

fal

Use when calling a fal.ai endpoint by id to generate image, audio, or video from JS/Python/curl: subscribe vs submit, queue states, ED25519 webhook signature verification, per-call cost, or migrating off @fal-ai/serverless-client. NOT which model or art direction (that is ai-media); NOT the same models on another…

ericrisco/rsc-harness · 78 tokens

gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

davila7/claude-code-templates · 84 tokens

sglang-diffusion-benchmark-profile

Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

sgl-project/sglang · 26 tokens

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

Emily2040/seedance-2.0 · 68 tokens