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 DeepKolor/deepkolor-agent-skills --skill video-agentgit clone --depth 1 https://github.com/DeepKolor/deepkolor-agent-skillsWrote 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/deepkolor/deepkolor-agent-skills/video-agent)<a href="https://agentmods.dev/skills/deepkolor/deepkolor-agent-skills/video-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/video-agent/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/deepkolor/deepkolor-agent-skills/video-agent"><img src="https://agentmods.dev/badge/skills/deepkolor/deepkolor-agent-skills/video-agent.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 | $0.00060 | $0.00444 |
| Opus 5 | $0.00030 | $0.00222 |
| Sonnet 5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
video-agent 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.
What it actually says
Video Agent
Lite edition — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on DeepKolor.
AI video prompts, storyboards, director treatments, and text-to-video generation.
When to use
See description in frontmatter — the agent loads it at startup for routing.
Workflow
- Default to prompt/storyboard output; call create_video_task only when the user clearly wants a video made.
- Prompts in English: subject, action, camera, lighting, audio, continuity, final image.
- Infer aspect ratio from use case (9:16 social, 16:9 cinematic).
- Typical clip length 5–15 seconds unless specified.
Defaults
durationSeconds 5–15, aspectRatio by platform
Tool: create_video_task
{
prompt: string,
durationSeconds?: number,
aspectRatio?: string,
cameraMotion?: string
}
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
Boundaries
- Video only — route still-image requests to the appropriate image skill.
- Wait for tool result before claiming success.
Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
Full version
Production-grade references (SOPs, templates, platform rules) ship inside DeepKolor — not in this public lite package.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 57 lines · 60 tokens per session scan A 268cd84f14cc
video-agent is a skill published in the GitHub repository DeepKolor/deepkolor-agent-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 444 once invoked, about $0.0003 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
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
videoagent-director
AI creative director that turns a user's natural-language idea into a complete storyboard and generates all assets — images, video clips, and audio — automatically. The user only describes what they want; all prompt engineering is handled internally.
minimax-h3-reference-video-prompt
Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio…
minimax-h3-keyframe-video-prompt
Narrow downstream MiniMax H3 specialist for pure I2VA, FL2VA, and L2VA boundary-frame prompts. Use only after minimax-h3-creative-director verifies that the user explicitly declared the images as literal first/last frames and that they have no character, identity, person, object, costume, scene, style, voice, action…
minimax-h3-multishot-planner
Non-skippable planning-only MiniMax H3 subskill used by minimax-h3-creative-director before final prompt formatting. Invoke when the user explicitly requests multiple shots, scenes, cuts, montage, or shot-by-shot design, or when a video of at least 10 seconds has no declared single-shot/multishot preference and the…
minimax-h3-text-video-prompt
Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format. Use after minimax-h3-creative-director routes a request with no image, video, or audio reference asset, or when this skill is explicitly invoked for a text-only idea, script, or storyboard requiring an…