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 calesthio/generative-media-skills --skill kling-videogit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/kling-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/kling-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/kling-video/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/calesthio/generative-media-skills/kling-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/kling-video.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00105 | $0.09596 |
| Opus 5 | $0.00053 | $0.04798 |
| Sonnet 5 | $0.00021 | $0.01919 |
| Haiku 4.5 | $0.00011 | $0.00960 |
Grade A, and why
kling-video scanned grade A with 2 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.parse import urlsplit Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
process = subprocess.Popen(argv, shell=False, stdin=subprocess.DEVNULL, How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce video with Kling AI
Treat model availability, API fields, prices, policies, and limits as volatile. The facts below were verified against first-party Kling/Kuaishou sources on 2026-07-10; reopen the linked model page, billing table, update log, and terms before spending or shipping.
Keep the surface and job coherent
Ask for the delivery surface (direct API or Kling web/app), geography, task, input media, duration, aspect ratio, resolution, audio/dialogue, shot structure, audience, rights/consent, privacy needs, variant count, and approved spend.
| Surface | Use it for | Keep separate |
|---|---|---|
| Direct international API | Server workflows at https://api-singapore.klingai.com; API-key auth; per-second API billing |
Old api.klingai.com, China-host routing, consumer credits, or a reseller schema |
| Kling web/app | Interactive creation, Elements library, memberships, free/paid UI features | A promise that UI controls, credits, watermark benefits, or defaults exist in API |
kling-v3 / VIDEO 3.0 |
Prompt-led text/image/start-end generation, native audio, flexible duration, multi-shot | Omni video editing/reference inputs |
kling-v3-omni / VIDEO 3.0 Omni |
Reference-driven generation, video/reference inputs, Elements, editing, native audio, multi-shot | Kling Image 3.0 Omni or Kolors |
kling-3.0-turbo |
Current faster, scale-oriented 3.0 option with native audio | An assumption that every 3.0 or Omni field is accepted unchanged |
| Motion Control | Transfer one driving performance to a referenced character | Avatar, lip-sync, face recognition, or standalone audio APIs |
FACT: The current API documentation requires the new API-key format for all models. Legacy AccessKey/SecretKey JWT credentials remain valid only for 3.0-and-earlier access and do not unlock new models. Use a server-side KLING_API_KEY; never expose it in a browser or mobile client. The current international host is Singapore, while China deployments have a different Beijing host. Do not select a host as a data-residency guarantee. Authentication
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.
- 9d ago First seen · 499 lines · 105 tokens per session scan A d27b0c011d6f
kling-video is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 9,596 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…