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 xai-grok-imagine-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/xai-grok-imagine-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/xai-grok-imagine-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/xai-grok-imagine-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/xai-grok-imagine-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/xai-grok-imagine-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 147 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 | $0.00120 | $0.13561 |
| Opus 5 | $0.00060 | $0.06781 |
| Sonnet 5 | $0.00024 | $0.02712 |
| Haiku 4.5 | $0.00012 | $0.01356 |
Grade A, and why
xai-grok-imagine-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.
import urllib.error Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
process = subprocess.Popen(argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE) How it starts
The opening of the file, as written. The whole thing — 704 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xAI Grok Imagine video
Use the direct xAI API as a controlled media-production service: freeze the creative brief and source rights, derive a priced request, persist intent before the paid POST, reconcile its asynchronous result, then preserve the artifact and its evidence.
All volatile facts and prices below were checked against xAI first-party sources on 2026-07-10.
Choose the correct production lane
The direct endpoint is https://api.x.ai. Authenticate server-side with Authorization: Bearer $XAI_API_KEY. API keys belong to xAI Console teams and use prepaid credit or invoiced API billing.
Do not blend these separate surfaces:
- Grok on
grok.comand the mobile apps uses consumer plans, weekly allowances, consumer data controls, and consumer terms. “Video 1.5 Fast†is advertised there but is not a direct-API model slug. - Grok on X is governed by X terms and privacy rules. An X Premium or SuperGrok subscription is not API credit.
- Grok Imagine image models use
/v1/images/*; voice and speech use other endpoints. Their parameters and prices do not transfer to video. - Partner platforms and gateways—including services named in xAI marketing—may wrap xAI models but add their own schema, moderation, retention, pricing, and regions.
- Azure, Google Cloud, and other managed offerings have separate authentication, quotas, feature parity, billing, and data-governance contracts. This skill describes xAI's direct API.
The public API uses api.x.ai. xAI advertises multiple inference clusters and enterprise data-residency options, while its status page shows US and EU regional API services. Do not select a regional hostname or promise residency from a page label alone. Use only the endpoint, region, and contractual controls provisioned for the team in xAI Console or its order form/DPA.
Model and mode decision board
Exactly one mode may be active per request.
| Goal | Endpoint and REST fields | Valid model | Output controls |
|---|---|---|---|
| Text-to-video | POST /v1/videos/generations; prompt |
grok-imagine-video |
duration 1–15 s; listed aspect ratios; 480p/720p |
| Image-to-video | generations; prompt + image |
either model | 1–15 s; listed aspect ratios; base: 480p/720p; 1.5: 480p/720p/1080p |
| Reference-to-video | generations; prompt + reference_images |
grok-imagine-video only |
1–10 s; listed aspect ratios; 480p/720p; 1–7 references |
| Edit video | POST /v1/videos/edits; prompt + video |
grok-imagine-video only |
no custom duration/aspect/resolution; input ≤8.7 s; output inherits duration/aspect and resolution capped at 720p |
| Extend video | POST /v1/videos/extensions; prompt + video |
grok-imagine-video only |
input 2–15 s; extension 2–10 s, default 6; output inherits aspect/resolution capped at 720p |
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 · 704 lines · 120 tokens per session scan A fe98e8cf128f
xai-grok-imagine-video is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 13,561 once invoked, about $0.0006 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
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
Tencent Cloud Infra
A command-line guide for managing Tencent Cloud services, including servers, networks, domains, certificates, storage, permissions, and monitoring. Tencent Cloud is a cloud provider, and tccli is its command-line tool.
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.
vigilante-issue-implementation-on-terraform
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Terraform repository with fmt, validate, and secret-safe infrastructure guidance.
aws
Skill "aws" from dhaupin/vant, covering aws, when to use, what to do, 1. services and 2. cli.
vLLM
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.