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.
curl -O https://raw.githubusercontent.com/jordanurbs/venice-video-harness/main/.agents/commands/set-aesthetic.mdgit clone --depth 1 https://github.com/jordanurbs/venice-video-harnessWrote 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/commands/jordanurbs/venice-video-harness/set-aesthetic)<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/set-aesthetic"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/set-aesthetic/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/commands/jordanurbs/venice-video-harness/set-aesthetic"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/set-aesthetic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00949 |
| Opus 5 | $0.00000 | $0.00475 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
set-aesthetic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/set-aesthetic
Auto-generate aesthetic comparison samples and let the user pick a visual style.
Behavior
Do NOT ask the user to describe a style verbally. Instead, generate visual samples and let them react to images.
If the user specifies a style (e.g., "set a noir look"):
Run the CLI directly:
npx tsx src/cli.ts set-aesthetic --project "$project_dir" --style "$style" --palette "$palette" --lighting "$lighting" --lens "$lens" --film "$film"
If the user says "set aesthetic" without specifying a style:
- Read the ingested project data to understand the screenplay's tone, setting, and genre
- Design 5-7 diverse aesthetic options that fit the material
- Write a temporary Node.js (.mjs) script that:
- Reads the Venice API key from
.envmanually (no dotenv import -- parse the file directly) - Calls
POST https://api.venice.ai/api/v1/image/generatefor each aesthetic - Uses model
nano-banana-pro, resolution1280x720(16:9),steps: 30,cfg_scale: 7 - Uses a representative scene description from the screenplay as the base prompt
- Appends aesthetic-specific style directives to each prompt
- Runs 2 requests at a time with 500ms delay between batches
- Extracts the image from
response.images[0](raw base64 string, NOT.b64_json) - Saves PNGs to
output/<project>/aesthetic-samples/<name>.png - Generates
compare.htmlfor side-by-side viewing
- Reads the Venice API key from
- Run the script with
node - Show each generated image to the user inline using the Read tool
- Describe each aesthetic in a few words
- Let the user pick one, request hybrids/tweaks, or ask for more options
- Once chosen, run
set-aestheticCLI with the selected parameters
Aesthetic Template Ideas
Adapt these to the screenplay's genre/setting:
- Neo-Noir Cyberpunk: Neon-lit, rain-slicked, deep blues/purples/pinks, volumetric fog, 35mm Kodak Vision3 500T
- Clean Dystopia: Sterile white corridors, clinical grays, flat fluorescent, symmetrical, Arri Alexa digital
- Retro-Futurism (Moebius): Bold linework, painted color, teals/oranges, ink and watercolor texture
- Gritty Anime Realism: Ghost in the Shell / Akira inspired, muted greens, industrial, cel-shaded hybrid
- Analog Sci-Fi 70s: Alien / THX 1138 aesthetic, chunky hardware, amber CRT glow, 16mm Ektachrome
- SNES Pixel Art: 16-32 bit pixel art, limited palette, dithering, isometric RPG perspective
- Wes Anderson Symmetry: Pastel palette, centered framing, dollhouse aesthetic, Futura typography
- Soviet Brutalism: Concrete textures, propaganda poster palette, stark shadows, 35mm Svema film
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.
- 12d ago First seen · 67 lines · 0 tokens per session scan A a4922da42bc4
set-aesthetic 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 949 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.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.