sdk: Skill for Claude Code

.claude/skills/varg-video-generation/SKILL.md

varg-video-generation is a skill for Claude Code from vargHQ/sdk. It costs 43 tokens per session (825 once invoked), scanned A, original, Apache-2.0.

A workflow for creating AI videos with the varg React engine, using code-like compositions that can combine images, video, music, voice, and captions.

In plain words
What is it for?
Use it to create videos, animations, talking characters, slideshows, and social-media content, provided the required Fal.ai key is configured.
Why use it?
It organizes video generation and can reuse cached results when the same inputs are used. It also checks whether the required API setup is available.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is vargHQ/sdk's own configuration. It tells Claude Code how to work on sdk 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 sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vargHQ/sdk. 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/vargHQ/sdk/main/.claude/skills/varg-video-generation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vargHQ/sdk

Made for: Claude Code.

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 varg-video-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/varghq/sdk/varg-video-generation/github.svg)](https://agentmods.dev/skills/varghq/sdk/varg-video-generation)
Your own site
<a href="https://agentmods.dev/skills/varghq/sdk/varg-video-generation"><img src="https://agentmods.dev/badge/skills/varghq/sdk/varg-video-generation/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 varg-video-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/varghq/sdk/varg-video-generation"><img src="https://agentmods.dev/badge/skills/varghq/sdk/varg-video-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 825 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: 2 findings, up to high

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 →

  • high Privilege Escalation · line 31
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 31
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 $0.00043 $0.00825
Opus 5 $0.00022 $0.00413
Sonnet 5 $0.00009 $0.00165
Haiku 4.5 $0.00004 $0.00082

Measured 9d ago against content hash 450a02f18f95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

varg-video-generation 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 9d 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.

.claude/skills/varg-video-generation/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Generation with varg React Engine

Overview

This rule helps you generate AI videos using the varg SDK's React engine. It provides:

  • Declarative JSX syntax for video composition
  • Automatic caching (same props = instant cache hit)
  • Parallel generation where possible
  • Support for images, video, music, voice, and captions

Step 1: Onboarding (REQUIRED for new users)

Before generating videos, ensure the user has the required API keys configured.

Check Current Setup

Run this command to check existing configuration:

cat .env 2>/dev/null | grep -E "^(FAL_KEY|ELEVENLABS_API_KEY|REPLICATE_API_TOKEN|GROQ_API_KEY)=" || echo "No API keys found in .env"

Required: FAL_KEY

This is the minimum requirement for video generation.

Detail Value
Provider Fal.ai
Get it https://fal.ai/dashboard/keys
Free tier Yes (limited credits)
Used for Image generation (Flux), Video generation (Wan 2.5, Kling)

If user doesn't have FAL_KEY:

  1. Direct them to https://fal.ai/dashboard/keys
  2. They need to create an account and generate an API key
  3. Add to .env file in project root

Optional Keys (warn if missing, but continue)

Feature Required Key Provider Get It
Music generation ELEVENLABS_API_KEY ElevenLabs https://elevenlabs.io/app/settings/api-keys
Voice/Speech ELEVENLABS_API_KEY ElevenLabs https://elevenlabs.io/app/settings/api-keys
Lipsync REPLICATE_API_TOKEN Replicate https://replicate.com/account/api-tokens
Transcription GROQ_API_KEY Groq https://console.groq.com/keys

When keys are missing, inform user what features are unavailable.

Step 2: Running Videos

bunx vargai render video.tsx

Key Components

Component Purpose Required Key
<Render> Root container -
<Clip> Sequential segment -
<Image> AI image FAL
<Video> AI video FAL
<Music> Background music ElevenLabs
<Speech> Text-to-speech ElevenLabs

Read the full file on GitHub · 98 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. 9d ago First seen · 98 lines · 43 tokens per session scan A 450a02f18f95

Subscribe to this mod's changes

varg-video-generation is a skill published in the GitHub repository vargHQ/sdk (337 stars, last pushed 8d ago), licensed Apache-2.0. It adds 43 tokens to every session and 825 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.

Related

Other skills, from other repositories

kling-ai

Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control…

maciejdzierzek/kling-ai-prompt-generator · 89 tokens

stage-compose

Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…

Orkas-AI/Orkas-VideoStudio · 96 tokens

frontend-design

Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.

Orkas-AI/Orkas-VideoStudio · 57 tokens

stage-edit

Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.

Orkas-AI/Orkas-VideoStudio · 62 tokens

stage-plan

The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…

Orkas-AI/Orkas-VideoStudio · 0 tokens

gate-control

Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…

Orkas-AI/Orkas-VideoStudio · 81 tokens