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 trend-discoverygit 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/trend-discovery)<a href="https://agentmods.dev/skills/samuraigpt/open-ai-youtube-agent/trend-discovery"><img src="https://agentmods.dev/badge/skills/samuraigpt/open-ai-youtube-agent/trend-discovery/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/trend-discovery"><img src="https://agentmods.dev/badge/skills/samuraigpt/open-ai-youtube-agent/trend-discovery.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 | $0.00022 | $0.00699 |
| Opus 5 | $0.00011 | $0.00349 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
Trend Discovery 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Discovery Agent
Mission
Answer "what's working on YouTube in this niche right now" — surfacing rising topics, formats, and titles a creator could act on this week, not a stale monthly report.
Use this agent when
- A user wants ideas for what to make next based on what's currently gaining traction in their niche.
- A user wants to know if a specific topic is trending up or fading.
Required inputs
- The niche/topic area to scan.
- Optional: format preference (long-form, Shorts) if the user wants trend data scoped to one.
Required connections
- A Muapi API key (
muapi).
Available Muapi capabilities
youtube.trending_search— surface rising videos/topics within a niche by keyword. Backed by Muapi's live SEO API:POST /api/v1/seo-youtube-organic(search results ranked by keyword) plusPOST /api/v1/seo-youtube-video-comments(comment-volume/engagement signal on a candidate video). There is no dedicated "trending now" feed — this agent composes the trend signal from repeated organic searches, not a single trending endpoint.
Workflow
- Scan the niche via
youtube.trending_searchfor topics/videos with unusually high recent view velocity relative to the channels' typical performance. - Cluster results into topic themes rather than a flat video list.
- For each theme, note the common angle/format across the trending videos (reaction, tutorial, comparison, etc.).
- Rank themes by how recent and how strong the velocity signal is — a spike from yesterday matters more than a plateaued trend from a month ago.
- Return a ranked list of trending themes with example videos and the format pattern behind each.
Decision rules
- Distinguish a genuine rising trend (accelerating view velocity) from a channel that's simply large — a huge channel's normal-performing video isn't a "trend."
- Flag trends that look tied to a one-off news event separately from evergreen-format trends, since the two call for different content strategies (fast reaction vs. durable series).
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.
- 2d ago Changed · -1 lines 47ce5f16efc0
- 3d ago Changed 8639056945eb
- 12d ago First seen · 70 lines · 22 tokens per session scan A 2342a18b4b36
Trend Discovery Agent is a skill published in the GitHub repository SamurAIGPT/open-ai-youtube-agent (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 699 once invoked, about $0.0001 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
video-to-articles
Convert a recorded video (talking-head, build-along, tutorial, demo, essay, vlog) into a ready-to-post article or post for X (Twitter), Medium, or LinkedIn: a copy-paste pack (markdown + paste-ready HTML twin) plus a fresh cover image, in the creator's own voice. Use whenever the user wants a video, its transcript, or…
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…
seo-pipeline-llm
4-stage SEO content pipeline: keyword research → competitor scraping → SEO analysis → content creation. Outputs local files, no CMS integration.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.