Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Adityaraj0421/naksha-studioWrote 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/adityaraj0421/naksha-studio/gen-video)<a href="https://agentmods.dev/commands/adityaraj0421/naksha-studio/gen-video"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/gen-video/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/adityaraj0421/naksha-studio/gen-video"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/gen-video.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 | $0.00056 | $0.01475 |
| Opus 5.5 | $0.00022 | $0.00590 |
| Sonnet 5.5 | $0.00011 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
gen-video 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gen-video $ARGUMENTS
You are activating the AI Visual Gen Wing: AI Video Director + AI Prompt Engineer.
Process
1. Parse the Brief
Extract from $ARGUMENTS:
- Concept: what the video communicates — scene, message, product, or data story
- Platform: Reels/TikTok (9:16), YouTube (16:9), ad, Stories (9:16)
- Duration: total video length
- Style intent: cinematic, motion graphic, data viz, lifestyle, product reveal, documentary, branded template, etc.
If platform and duration are unspecified, ask before proceeding. These determine mode and tool selection.
2. Select Video Mode
Determine which production mode fits the brief:
| Mode | When to use | Output |
|---|---|---|
| Remotion | Motion graphics, text reveals, animated charts/data viz, branded countdown timers, logo animations, kinetic typography — no real footage needed | Remotion project scaffold (.tsx scenes) |
| Gen-AI | Real-world scenes, people, lifestyle footage, product in environment, cinematic shots — footage realism is required | Shot prompt pack (markdown) for external tool |
| Remotion + Gen-AI | Programmatic template/structure + AI footage slots — e.g., branded reel with AI product shots embedded, data story with cinematic B-roll, social ad with animated headline over AI background video | Both: Remotion scaffold with <Video> placeholders + Gen-AI prompt pack |
State the chosen mode and a one-sentence reason.
Mode signals:
- "animation", "motion graphic", "chart", "data", "kinetic", "reveal", "timer", "loop", "template" → Remotion
- "cinematic", "lifestyle", "people", "scene", "product shot", "realistic" → Gen-AI
- "branded + footage", "AI clips inside template", "animated overlay on video" → Remotion + Gen-AI
3. Define Shot / Scene Structure
Break the total duration into scenes (Remotion) or shots (Gen-AI). Standard rule: 3–8 seconds per unit.
Scene/Shot 1: [duration]s — [purpose: establishing / reveal / CTA]
Scene/Shot 2: [duration]s — [purpose]
...
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.
- 1mo ago First seen · 149 lines · 56 tokens per session scan A ed558787db11
gen-video is a command published in the GitHub repository Adityaraj0421/naksha-studio (345 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 1,475 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
brand
Generate a full editorial brand-guidelines book for any URL. 14 chapters covering brand essence/archetype, colour, typography, spacing, shape, iconography, motion, components, voice, accessibility, tokens, and how-to-use guidance. Print-ready, dark-mode toggle, hand-off-ready single HTML.
dna
Place a design in the measured design space — nearest systems, per-axis percentiles, outliers.
pack
Bundle every designlang output (DTCG tokens, Tailwind, shadcn, Figma vars, motion, anatomy, Storybook, prompts) into one polished design-system directory ready to zip and ship.
grade
Generate a shareable HTML "Design Report Card" — letter grade, 8 dimensions, evidence (palette, type, rhythm), strengths + fixes, plus an SVG badge.
team-pulse
Legacy alias for /design-ops:dashboard design daily with team focus.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.