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 SamurAIGPT/open-ai-youtube-agent --skill video-seo-optimizationgit clone --depth 1 https://github.com/SamurAIGPT/open-ai-youtube-agentWrote 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/samuraigpt/open-ai-youtube-agent/video-seo-optimization)<a href="https://agentmods.dev/skills/samuraigpt/open-ai-youtube-agent/video-seo-optimization"><img src="https://agentmods.dev/badge/skills/samuraigpt/open-ai-youtube-agent/video-seo-optimization/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/samuraigpt/open-ai-youtube-agent/video-seo-optimization"><img src="https://agentmods.dev/badge/skills/samuraigpt/open-ai-youtube-agent/video-seo-optimization.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 | $0.00032 | $0.01169 |
| Opus 5 | $0.00016 | $0.00584 |
| Sonnet 5 | $0.00006 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
Video SEO Optimization 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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video SEO Optimization Agent
Mission
Turn a finished video and a topic brief into a keyword-considered title, description, tags, and a legible-text thumbnail, then publish it to a connected YouTube account — without a human manually filling in metadata fields one at a time.
Use this agent when
- A user has a video ready to upload and wants SEO-considered metadata drafted before publishing.
- A user wants a few title/thumbnail variants to choose between.
- A user wants to schedule the upload rather than publish immediately.
Required inputs
- The video's core topic and hook.
- A hosted media URL for the finished video (or a local file — upload it first via
media.upload_file, see MODELS.md for the endpoint). - A connected YouTube account (see
ai-social-agent). - Optional: target keywords, if the user already knows them.
- Optional: publish time (immediate or scheduled).
Required connections
- A Muapi API key (
muapi). - A connected YouTube account via Muapi's social OAuth flow.
Available Muapi capabilities
seo.keyword_research(POST /seo-keyword-research) — general Google keyword-volume/related-term data, used as an imperfect proxy for YouTube search demand (no YouTube-specific keyword endpoint is live yet — see this repo's README for the DataForSEO YouTube SERP gap).media.generate_image— generates the thumbnail; pick a text-capable model (e.g.qwen-image,gpt-image-2) perai-image-agent's MODELS.md, since a thumbnail needs legible overlay text.social.list_accounts(GET /social/accounts) — confirm the connected YouTube account before publishing.social.publish(POST /social/publish) — uploads the video with title, description (caption), and tags to the connected account, immediately or at a scheduled time.
Workflow
- Confirm a connected YouTube account exists via
social.list_accounts; if not, report that and stop. - If target keywords weren't supplied, propose a candidate set from the topic brief and confirm real search interest via
seo.keyword_research(noting it's a Google-data proxy, not native YouTube search volume). - Draft 2-3 title variants that include the primary keyword near the start without becoming unreadable clickbait.
- Draft a description: first 2-3 lines optimized for the "show more" preview, remaining lines with supporting context and secondary keywords, avoiding keyword stuffing.
- Draft a tag list: primary keyword, close variants, and broader category tags.
- Generate 2-3 thumbnail concepts via
media.generate_imageusing a text-capable model, followingai-image-agent's thumbnail-generation conventions. - Present the full draft (title options, description, tags, thumbnail options) for approval.
- On approval, call
social.publishwith the chosen title/description/tags/thumbnail-referenced video, immediately or withscheduled_at.
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 · 84 lines · 32 tokens per session scan A 863d7a06662d
Video SEO Optimization Agent is a skill published in the GitHub repository SamurAIGPT/open-ai-youtube-agent (2 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,169 once invoked, about $0.0002 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
shorts-from-takes
Assemble several raw clips — multiple takes, separate shots, or existing reels — into ONE finished, on-brand vertical Short (1080x1920), PLUS ready-to-post YouTube / Instagram / TikTok / X metadata. Use this whenever someone hands over a batch of clips and wants them stitched into a single short-form video: it selects…
content-pipeline
A Chinese-language workflow for turning collected source material into articles and versions for several publishing platforms, including formatted previews, cover images, social posts, podcasts, and videos.
longform-to-shorts
Cut standalone vertical Shorts/Reels (1080x1920) out of ONE finished long-form talking-head + screen-share video (a "N tools" walkthrough, tutorial, review, demo), one Short per topic/tool, then write per-Short YouTube + Instagram metadata. Use this whenever the user hands over a finished long-form video and wants…
youtube-shorts-generator
Generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or local video. Triggers on requests like "make shorts from this video", "extract viral clips from this YouTube link", "auto-clip this podcast", "find the best moments and crop vertical". Pipeline downloads the source, transcribes…
omh-image-cards
This is a Hermes-native img-summary workflow skill.
short-drama
A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.