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 vidu-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/vidu-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/vidu-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/vidu-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/vidu-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/vidu-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 217 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00093 | $0.07713 |
| Opus 5 | $0.00046 | $0.03857 |
| Sonnet 5 | $0.00019 | $0.01543 |
| Haiku 4.5 | $0.00009 | $0.00771 |
Grade A, and why
vidu-video scanned grade A with 1 finding 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.
import datetime, hashlib, json, os, pathlib, sys, urllib.error, urllib.request How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vidu video
Use this skill to design a production request or integration for the Vidu Open Platform API. Default to dry-run planning. Never submit a paid generation, upload private media, cancel a task, or download a result until the operator has approved the exact provider, endpoint, model, inputs, request digest, maximum charge, storage destination, and disclosure plan.
This document was verified against first-party public documentation on 2026-07-10. Models, prices, accepted fields, policies, and availability are volatile; re-open the linked endpoint and pricing pages immediately before execution.
Keep the surfaces separate
- Open Platform API:
https://api.vidu.com, API keys, organization-level limits, asynchronous tasks, and API credits. This is the surface covered here. - Vidu consumer product:
https://www.vidu.comand its subscription/plan credits. Do not assume its credits, features, watermark behavior, or terms apply to the API. - Vidu-S1 (Beta): a separate interactive digital-human product using HTTP session setup, AliRTC media, and WebSocket control. It is not a Q3/Q2 clip model. Its public page currently mixes “1 minute to 2 hours” marketing language with a 600-second session maximum. Its pricing section separately says 3 S1 credits per 2 seconds, lists a
0.03125credit unit price, deducts every 6 seconds, rounds to 2-second intervals, and requires at least 45 credits to create a session. Do not revalue those statements using the clip API's$0.005credit price without written confirmation. - S1 documentation conflict: Step 3 says browser WebSocket authentication belongs in the URL query because browsers cannot set custom headers, while the page's Important Notes says it must be in an authorization header. Treat this as unresolved. Confirm the current transport with Vidu before implementation, never place a bearer URL in logs/analytics/referrers, and do not infer a secure browser design from the sample alone.
- China host: the S1 page documents
api.vidu.cnfor China andapi.vidu.cominternationally. The ordinary clip endpoints documented here useapi.vidu.com; do not infer compute residency from the hostname.
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 · 385 lines · 93 tokens per session scan A 093aa22ac2d3
vidu-video is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 7,713 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…