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/seevido-prompt-mcp --skill seevido-video-prompt-architectgit clone --depth 1 https://github.com/gpt-img-2/seevido-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/seevido-prompt-mcp/seevido-video-prompt-architect)<a href="https://agentmods.dev/skills/gpt-img-2/seevido-prompt-mcp/seevido-video-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/seevido-prompt-mcp/seevido-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/seevido-prompt-mcp/seevido-video-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/seevido-prompt-mcp/seevido-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 | $0.01156 |
| Opus 5 | $0.00039 | $0.00578 |
| Sonnet 5 | $0.00016 | $0.00231 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
seevido-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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SeeVido Video Prompt Architect
Turn one clear visual idea into production-ready video instructions. This Skill is a text-only workflow by default. Its optional MCP adds deterministic, read-only helpers and never generates media, calls a provider, reads an account, compares live prices, or spends credits.
SeeVido is an independent AI media workspace. Do not present this Skill, the MCP, or the site as official documentation for Seedance, Kling, Wan, Grok, Veo, or any other provider or model.
Gather the minimum brief
Ask only for details that materially change the result. Infer ordinary creative choices when enough context already exists.
Identify:
- Workflow: text-to-video, image-to-video, reference-to-video, or video-to-video.
- Subject and environment.
- One primary visible action per shot.
- Camera framing, movement, and pace.
- Duration and aspect ratio when known.
- The role of every
@Image,@Video, or@Audioreference. - Identity, product geometry, composition, motion, timing, or audio that must remain stable.
- Delivery goal: product clip, cinematic beat, social post, transition, loop, or sequence.
Never invent model-specific controls, limits, input support, prices, or availability. Use the current product interface as the source of truth when exact settings matter.
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 roles and continuity constraints.
- A short artifact-focused avoid list.
Prefer observable instructions over abstract mood. Keep subject motion separate from camera motion. Avoid simultaneous competing actions, contradictory camera commands, and long style lists.
For image-to-video, preserve identity, layout, lighting direction, and geometry unless transformation is requested. For reference-to-video, keep every token exactly as supplied and assign one clear role per reference. For video-to-video, state which source motion, timing, camera path, and scene structure must survive.
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 · 105 lines · 79 tokens per session scan A 54426d24ec52
seevido-video-prompt-architect is a skill published in the GitHub repository gpt-img-2/seevido-prompt-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 79 tokens to every session and 1,156 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
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…
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…
opensora-video-prompt-architect
Turn rough video ideas into structured OpenSora prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for unrelated models, account support, or…
video-prompt-engineer
A workflow for converting a finished script or script excerpt into Seedance-ready storyboards and video prompts. Seedance is an AI video-generation system, and each storyboard covers a 10–15-second clip.
ai-film-production-system
Project-level production control for AI short films and case-informed AI drama pipelines using the v2 generic film protocol. Use when working with a movie root, project state, constraints, task queues, character/scene/prop bibles, shot plans, prompt specs, assets, manifests, provider batches, Dreamina/Seedance-style…
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…