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 cosmicstack-labs/mercury-agent-skills --skill youtube-research-automationgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/youtube-research-automation)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/youtube-research-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/youtube-research-automation/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/cosmicstack-labs/mercury-agent-skills/youtube-research-automation"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/youtube-research-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 MCP Rug Pull · line 95 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 168 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00031 | $0.02077 |
| Opus 5 | $0.00015 | $0.01038 |
| Sonnet 5 | $0.00006 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
youtube-research-automation 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_ID&format=text" \ How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Research Automation
Use this skill when an agent needs to read what was said in a video, find videos or channels on a topic, walk a channel or playlist, or watch a channel for new uploads, and you want that to run as a repeatable workflow rather than a manual copy and paste.
Recommended implementation:
- youtube-skills for any
runtime that supports the Agent Skills format. It ships twelve skills, and
youtube-fullcovers transcripts, video and channel search, channel browsing, and playlist extraction in one install. - youtube-mcp when the runtime speaks MCP instead of skills. Same tools, remote endpoint, API key or OAuth.
Both call TranscriptAPI, an independent REST API for YouTube content. It is not affiliated with YouTube or Google, and it is not the official YouTube Data API. That is the point of using it here: no Google Cloud project, no OAuth consent screen, and no daily quota unit accounting.
When to Use
Use this skill when the user asks for:
- The transcript, captions, or subtitles of a video, or a summary of one.
- Quotes, claims, timestamps, or numbers taken from a talk, lecture, or review.
- Videos or channels about a topic, without a browser in the loop.
- Every video on a channel, or a channel's recent uploads.
- Every video in a playlist, with titles and IDs.
- A recurring job that checks a channel and reports what is new.
- Research where video is fresher or more specific than written sources.
Do not use this skill for:
- Downloading or re-hosting video or audio files. This is a text and metadata workflow, and republishing someone's content is a licensing question, not a technical one.
- Uploading, commenting, account management, or anything that writes to YouTube.
- Videos with no captions. There is no transcript to fetch, so plan a fallback.
- Private or unlisted content the user does not own.
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 · 205 lines · 31 tokens per session scan A 868095974bc3
youtube-research-automation is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 31 tokens to every session and 2,077 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.