What is youtube-research?

A research workflow for finding credible creators and analysing their videos and Instagram Reels for a chosen subject.

Use it to find videos about a niche, compare channels by views or credibility measures, and extract video transcripts or Instagram content.

It provides commands for discovering relevant content, retrieving transcripts, and ranking results without relying on YouTube search quotas in the default workflow.

youtube-research — Skill for Claude Code by roarista

Install

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.

Any agent

npx skills add roarista/awesome-harness --skill youtube-research

Clone the repo

git clone --depth 1 https://github.com/roarista/awesome-harness

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/roarista/awesome-harness/youtube-research/github.svg)](https://agentmods.dev/skills/roarista/awesome-harness/youtube-research)

Your own site

<a href="https://agentmods.dev/skills/roarista/awesome-harness/youtube-research"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/youtube-research/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/roarista/awesome-harness/youtube-research"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/youtube-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,188 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00097	$0.01188
Opus 5	$0.00048	$0.00594
Sonnet 5	$0.00019	$0.00238
Haiku 4.5	$0.00010	$0.00119

Measured 11d ago against content hash c8e80904ce68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

youtube-research 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (discover_keyless.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/youtube-research/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive the global ytintel CLI (~/.local/bin/ytintel, on PATH, runs via uv). Keys are already global (~/.zshrc + ~/.config/ytintel/.env). YouTube is free/unlimited; Instagram uses ScrapeCreators credits (~1/call, finite) — be economical on IG, generous on YouTube.

When the user asks to research a topic/niche

Find videos — DEFAULT to keyless discovery (no API key, no quota):
```
python3 ~/.claude/skills/youtube-research/discover_keyless.py "query one" "query two" ... [--per 10] [--top 15]
```
Uses yt-dlp ytsearch under the hood — zero quota, never 429s, and in practice returns MORE on-target results than the Data API. Prints id | views | dur | channel | title sorted by views, plus an IDS: line. Pass several query phrasings to widen the pool; it dedups + ranks by view_count. Tradeoff vs the API: no cred_channel/engagement score — rank by views + manual relevance. Prefer this for almost everything.

Fallback — Data API discover (only if you need engagement/credibility scoring):
```
ytintel discover --topic "<the niche/topic>" --min-subs 20000 --min-er 0.02 --top 15
```
Ranked by cred_channel then cred_video. Costs ~100 quota units/call (single YOUTUBE_API_KEY, 10k/day). If it returns 429, the key is quota/rate-blocked → switch to keyless above (don't burn time on backoff). For higher API volume, keep a key list and rotate (see Notes).
Pull transcripts of the top videos (free):
```
ytintel transcript "<video url or id>"
```
Do this for the top N from step 1 to mine their actual method/claims. The Data API does NOT give transcripts — this is the piece that makes the research real.
Mine comments for VOC (free):
```
ytintel comments <video_id> --max 100
```
Top comments = audience questions, objections, "where do I get this" buy-signals, content gaps.

Read the full file on GitHub · 75 lines

Files

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.

discover_keyless.py 1.9 KB runs code

Changes

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.

11d ago First seen · 75 lines · 97 tokens per session scan A c8e80904ce68

Subscribe to this mod's changes

youtube-research is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 16d ago), licensed MIT. It adds 97 tokens to every session and 1,188 once invoked, about $0.0005 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 2026-08-31.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens