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 gpt-img-2/opensora2-prompt-mcp --skill opensora-video-prompt-architectgit clone --depth 1 https://github.com/gpt-img-2/opensora2-prompt-mcpWrote 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/gpt-img-2/opensora2-prompt-mcp/opensora-video-prompt-architect)<a href="https://agentmods.dev/skills/gpt-img-2/opensora2-prompt-mcp/opensora-video-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/opensora2-prompt-mcp/opensora-video-prompt-architect/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/skills/gpt-img-2/opensora2-prompt-mcp/opensora-video-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/opensora2-prompt-mcp/opensora-video-prompt-architect.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 | $0.00079 | $0.01195 |
| Opus 5 | $0.00039 | $0.00598 |
| Sonnet 5 | $0.00016 | $0.00239 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
opensora-video-prompt-architect 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSora Video Prompt Architect
Build production-ready video instructions from one clear visual idea. This Skill is a text-only workflow by default. Its optional MCP adds deterministic, read-only helpers and never generates a video, calls a model provider, reads an account, or spends credits.
OpenSora2.com is an independent OpenSora 2 resource and generation workspace. Do not present this Skill, the MCP, or the site as the official Open-Sora project or as authoritative model documentation.
Gather the minimum brief
Ask only for details that materially change the result. Infer ordinary creative choices when the user has already supplied enough information.
Identify:
- Workflow: text-to-video, image-to-video, or video-to-video.
- Subject and environment: what must remain recognizable.
- Visible action: one primary motion per shot.
- Camera: framing, angle, movement, and pace.
- Duration and aspect ratio when known.
- Reference constraints: identity, product geometry, wardrobe, composition, or source motion to preserve.
- Delivery goal: product clip, cinematic beat, social post, transition, loop, or sequence.
Never invent model-specific controls, limits, or supported settings. If the product interface is the source of truth, direct the user to the relevant workflow page.
Build the prompt
Write in this order:
- Subject and scene.
- One visible action.
- Camera framing and one motivated camera move.
- Lighting and visual treatment.
- Duration and aspect ratio if confirmed.
- Reference and continuity constraints.
- A short avoid list for likely artifacts.
Prefer observable instructions over abstract mood. Keep subject motion distinct from camera motion. Avoid multiple simultaneous actions, contradictory camera commands, and long style lists.
For image-to-video, preserve the source image's identity, layout, lighting direction, and object geometry unless the user requests a transformation. For video-to-video, state which source motion, timing, camera path, and scene structure must survive the transformation.
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.
- 11d ago First seen · 116 lines · 79 tokens per session scan A 3102e028b6d3
opensora-video-prompt-architect is a skill published in the GitHub repository gpt-img-2/opensora2-prompt-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 79 tokens to every session and 1,195 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
china-video-prompt-architect
Turn rough China AI video ideas into structured English or Chinese prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for…
see-dance-2-video-prompt-architect
Turn rough video ideas into structured English or Chinese Seedance-oriented prompt packs, exact reference bindings, shot sequences, and focused debugging loops. Use for text-to-video, image-to-video, multimodal reference, product clips, cinematic scenes, transitions, or loops; do not use for account support, live…
gpt-image-2-prompt-architect
Research real GPT Image 2 prompt examples and turn rough image ideas into structured prompt packs, reference-image edit instructions, product visuals, layouts, and debugging loops. Use for prompt search, prompt rewriting, ecommerce images, readable text, posters, social creatives, character sheets, storyboards, or…
minimax-h3-prompting
Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…
ai-video-prompt-generator
Generate AI video prompts from clean structured prompt specs, validate prompt specs, run an isolated OpenAI-based prompt generator, and lint prompt outputs for viewpoint, action, reference, dialogue, negative prompt, audio prompt, safety tags, and legacy-contamination failures. Use when producing or repairing…
universal-video-prompt-skill
Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.