venice-video-harness: Command for Claude Code

.agents/commands/generate-videos.md

generate-videos is a command for Claude Code from jordanurbs/venice-video-harness. It costs 0 tokens per session (1,171 once invoked), scanned A, original, MIT.

A command that turns storyboard panel images into short video clips, linking shots so the last frame of one shot can start the next.

In plain words
What is it for?
Use it to generate videos for all shots in a selected screenplay scene from a project directory, with a chosen video model if needed.
Why use it?
It removes the need to create each clip manually and helps keep nearby shots visually connected.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: installed under .agents/ (shared by several agents).

This is jordanurbs/venice-video-harness's own configuration. It tells Claude Code how to work on venice-video-harness 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 venice-video-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jordanurbs/venice-video-harness. 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/jordanurbs/venice-video-harness/main/.agents/commands/generate-videos.md
Clone the repo
git clone --depth 1 https://github.com/jordanurbs/venice-video-harness

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 generate-videos

README.md
[![agentmods](https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/generate-videos/github.svg)](https://agentmods.dev/commands/jordanurbs/venice-video-harness/generate-videos)
Your own site
<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/generate-videos"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/generate-videos/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 generate-videos

Your own site · 80×15
<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/generate-videos"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/generate-videos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,171 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.
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 $0.00000 $0.01171
Opus 5 $0.00000 $0.00585
Sonnet 5 $0.00000 $0.00234
Haiku 4.5 $0.00000 $0.00117

Measured 12d ago against content hash e3c02538ae71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

generate-videos 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/commands/generate-videos.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/generate-videos

Generate video clips from storyboard panel images using Venice AI's image-to-video models with frame chaining for visual continuity.

Usage

/generate-videos --project <project-dir> --scene <scene-number> [--model <model>]

Arguments

  • --project: Project output directory (required)
  • --scene: Scene number to generate videos for (required)
  • --model: Video model to use (optional, default: kling-o3-pro-image-to-video)

Execution

Run the frame-chaining video generation script from the project root:

npx tsx scripts/generate-scene-videos.ts <project-dir> <scene-number> [model]

IMPORTANT: Must be run from the project root directory (long-form-ai-vidgen/), not from a subdirectory.

What This Does

  1. Discovers all shot-NNN.video.json files in the scene directory
  2. Processes shots sequentially with frame chaining:
    • Shot 1: image_url = panel PNG (storyboard image as first frame)
    • Shot N>1: image_url = last frame extracted from previous video via ffmpeg
    • Kling O3 Pro only: end_image_url = next shot's panel PNG (composition target)
  3. For each shot: a. Reads shot-NNN.video.json for prompt, duration, and model config b. Encodes the appropriate image (panel or last frame) as base64 data URI c. Queues video via POST /api/v1/video/queue d. Polls POST /api/v1/video/retrieve every 10s until MP4 is returned e. Archives existing MP4 as shot-NNN-v1.mp4 if present f. Saves the resulting MP4 as shot-NNN.mp4 g. Extracts the last frame via ffmpeg for chaining to the next shot h. Calls POST /api/v1/video/complete for cleanup
  4. Reports progress after each shot

Prerequisites

  • Storyboard panels must be generated first (/storyboard-scene or /storyboard-all)
  • shot-NNN.png and shot-NNN.video.json files must exist in the scene directory
  • VENICE_API_KEY must be set in .env
  • ffmpeg and ffprobe must be on PATH (used for last-frame extraction)

Read the full file on GitHub · 108 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 · 108 lines · 0 tokens per session scan A e3c02538ae71

Subscribe to this mod's changes

generate-videos is a command published in the GitHub repository jordanurbs/venice-video-harness (30 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,171 tokens. 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.