AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.
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.
npx skills add inclusionAI/AWorld --skill video_script_writtinggit clone --depth 1 https://github.com/inclusionAI/AWorldWrote 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/skills/inclusionai/aworld/video_script_writting)<a href="https://agentmods.dev/skills/inclusionai/aworld/video_script_writting"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/video_script_writting.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01797 |
| Opus 5 | $0.00064 | $0.00898 |
| Sonnet 5 | $0.00026 | $0.00359 |
| Haiku 4.5 | $0.00013 | $0.00180 |
Grade A, and why
ai-video-script-sop-remotion-diffusion 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 8d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Core narrative rules (narrative DNA)
To keep the video engaging (“satisfaction”), the script should follow:
- Single hero: One core character drives the story through action that solves the problem.
- Show, don’t tell: No inner monologue; emphasize what happens on screen.
- Three-part arc:
- Opening (hook): A clear, seemingly impossible big task.
- Middle (grind): Dense, fast execution (cathartic, orderly).
- Ending (payoff): A strong visual reward.
- Radical brevity: Voice and subtitles stay 1:1; lines only announce or briefly react—let the pictures carry meaning.
2. Technical specs and limits
- Total length: $1\ \text{min}$–$3\ \text{min}$.
- Segment length: Must be an integer in seconds (e.g. $4.5\text{s} \rightarrow 5\text{s}$). Diffusion clips are capped at $10\text{s}$ per segment.
- Resolution: $1080\text{p}$ or $720\text{p}$.
- Frame rate: $24\text{fps}$ or $30\text{fps}$.
- Mandarin VO baseline: Plan copy at about 4–5 characters per second.
3. Shot tech-selection matrix
| Need | Recommended tech | Why | Avoid |
|---|---|---|---|
| Photoreal / complex lighting | Diffusion (video) | Texture, mood, physics, transitions. | On-screen text or charts in the same shot; don’t mix code and diffusion in one lens. |
| Character close-up / background change | Diffusion (I2V) | Image-to-video keeps continuity. | Control physical camera motion strictly. |
| Cartoon / vector motion | Code (SVG/TSX) | Clean edges, flat look, precise paths. | Hard to express rich texture. |
| Info / formulas / charts | Code (HTML/Remotion) | Exact typography, math, data. | Don’t use for photoreal landscapes. |
4. Diffusion prompt protocol
This is what keeps visuals high quality and coherent. Every diffusion shot description should combine five parts:
$$ \text{Prompt} = \text{[Style anchor]} + \text{[Micro-timeline]} + \text{[Concrete entities]} + \text{[Camera physics]} + \text{[Physical bridge]} $$
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.
- 8d ago First seen · 129 lines · 129 tokens per session scan A b3635d5cf235
ai-video-script-sop-remotion-diffusion is a skill published in the GitHub repository inclusionAI/AWorld (1,229 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 1,797 once invoked, about $0.0006 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.
Other skills, from other repositories
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
agenthub
Browse, create, and complete tasks on Clawsy AgentHub — a distributed task platform for AI agents. Create tasks from GitHub repos, PDF/DOCX/PPTX/audio URLs, or plain text. Use custom LLM validation, earn karma. Categories: content, data, research, creative.
citedy-content-ingestion
Turn any URL into structured content — YouTube videos (via Gemini Video API), web articles, PDFs, and audio files. Extract transcripts, summaries, and metadata for use in any LLM pipeline. Powered by Citedy.
video-model-selection
Choose which fal.ai or Google Gemini/Veo model fits one shot's requirements -- text-to-video vs image-to-video, character/subject consistency, duration limits, native audio, cost. Use before the first generation call in a long-form production, and again whenever a shot's requirements differ from the ones already…
video-look-sound
Lock the visual world and complete audio direction before narration or footage generation. Use when deciding locations, backgrounds, wardrobe, lighting, palette, narrator or dialogue voice, music, ambience, sound effects, captions, and whether speech should be separate TTS or native model audio.
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.