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 aedev-tools/kling-3-prompting-skill --skill kling-3-promptinggit clone --depth 1 https://github.com/aedev-tools/kling-3-prompting-skillWrote 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/aedev-tools/kling-3-prompting-skill/kling-3-prompting)<a href="https://agentmods.dev/skills/aedev-tools/kling-3-prompting-skill/kling-3-prompting"><img src="https://agentmods.dev/badge/skills/aedev-tools/kling-3-prompting-skill/kling-3-prompting/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/aedev-tools/kling-3-prompting-skill/kling-3-prompting"><img src="https://agentmods.dev/badge/skills/aedev-tools/kling-3-prompting-skill/kling-3-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00056 | $0.02310 |
| Opus 5 | $0.00028 | $0.01155 |
| Sonnet 5 | $0.00011 | $0.00462 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
kling-3-prompting 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 12d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Kling 3.0 is a unified multimodal video model. It understands cinematic direction, not keyword lists. Write prompts like a director — describe what the audience sees, hears, and feels over time.
Core shift: Description → Direction. Think "direct a scene" not "describe an image."
Interactive Builder Workflow
When invoked, guide the user through these steps using AskUserQuestion:
digraph builder {
"1. Generation mode?" [shape=diamond];
"Text-to-Video" [shape=box];
"Image-to-Video" [shape=box];
"Multi-Shot Sequence" [shape=box];
"Keyframe Transition" [shape=box];
"2. Gather scene details" [shape=box];
"3. Assemble prompt" [shape=box];
"4. Present & refine" [shape=box];
"1. Generation mode?" -> "Text-to-Video";
"1. Generation mode?" -> "Image-to-Video";
"1. Generation mode?" -> "Multi-Shot Sequence";
"1. Generation mode?" -> "Keyframe Transition";
"Text-to-Video" -> "2. Gather scene details";
"Image-to-Video" -> "2. Gather scene details";
"Multi-Shot Sequence" -> "2. Gather scene details";
"Keyframe Transition" -> "2. Gather scene details";
"2. Gather scene details" -> "3. Assemble prompt";
"3. Assemble prompt" -> "4. Present & refine";
}
Step 1: Determine Generation Mode
Ask the user which mode:
- Text-to-Video — prompt from scratch
- Image-to-Video — animate a reference image
- Multi-Shot Sequence — 2-6 shot storyboard (up to 15s)
- Keyframe Transition — start frame → end frame with interpolated motion
Step 2: Gather Scene Details
Ask about each element (adapt questions to mode):
| Element | Question | Why it matters |
|---|---|---|
| Subject | Who/what is the focus? Specific appearance details? | Anchors consistency — define distinguishing traits early |
| Action | What happens? Describe the timeline (first → then → finally) | Kling 3.0 excels at sequential action over 15s arcs |
| Environment | Where? Be specific (not "a street" but "narrow Tokyo alley, steam from grates") | Grounds the scene physically |
| Camera | Shot type and movement? (See camera reference below) | Cinematic language produces far better results |
| Lighting | What light sources? Name them specifically | "Flickering neon" beats "dramatic lighting" |
| Mood/Emotion | What should the audience feel? | Drives color grade, pacing, music |
| Audio | Dialogue? Ambient sound? Music? | Kling 3.0 generates native audio + lip-sync |
| Duration | How long? (3-15s) | Longer = describe progression over time |
| Aspect Ratio | 16:9 / 9:16 / 1:1 / 21:9? | 16:9 cinematic, 9:16 social, 21:9 ultra-wide |
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.
- 12d ago First seen · 211 lines · 56 tokens per session scan A 7a0764eae366
kling-3-prompting is a skill published in the GitHub repository aedev-tools/kling-3-prompting-skill (24 stars, last pushed 7mo ago), licensed MIT. It adds 56 tokens to every session and 2,310 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 2026-08-30.
Other skills, from other repositories
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.