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 fetcher-sh/fetcher-skills --skill youtube-apigit clone --depth 1 https://github.com/fetcher-sh/fetcher-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/fetcher-sh/fetcher-skills/youtube-api)<a href="https://agentmods.dev/skills/fetcher-sh/fetcher-skills/youtube-api"><img src="https://agentmods.dev/badge/skills/fetcher-sh/fetcher-skills/youtube-api/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/fetcher-sh/fetcher-skills/youtube-api"><img src="https://agentmods.dev/badge/skills/fetcher-sh/fetcher-skills/youtube-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
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 | $0.00151 | $0.02001 |
| Opus 5 | $0.00076 | $0.01001 |
| Sonnet 5 | $0.00030 | $0.00400 |
| Haiku 4.5 | $0.00015 | $0.00200 |
Grade A, and why
youtube-api 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 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.
curl -H "Authorization: Bearer $FETCHER_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube API
YouTube data on demand: video/channel/playlist search with real filters (upload date, duration, sort order), channel and video lookups, videos, shorts, live streams, playlist contents, comments, hashtag feeds, and trending — one plain HTTP GET per call, paid as you go. No developer console project, no OAuth consent screen, no daily quota.
Base URL: https://youtube.fetcher.sh
Authentication
Two ways to pay, same data — full mechanics in the fetcher
skill:
# 1. Prepaid credits (recommended — get a key at https://fetcher.sh/topup
# or via POST /api/credits/topup, see the fetcher skill)
export FETCHER_API_KEY="bby_live_xxxxxxxxxxxx"
curl -H "Authorization: Bearer $FETCHER_API_KEY" \
"https://youtube.fetcher.sh/api/search/video?query=hello"
# 2. x402 pay-per-call — omit the header; a GET with no payment returns 402
# with machine-readable payment requirements (USDC on Base, Polygon,
# Arbitrum, Monad, or Solana). @x402/fetch signs and retries automatically.
Every response is { "status": number, "message": string, "data": ... }; the
HTTP status mirrors status.
Endpoints (15 — all GET, $0.005/call)
| Endpoint | What it returns |
|---|---|
/api/search/video |
Videos matching a query; upload date, duration, sort filters |
/api/search/channel |
Channels matching a query |
/api/search/playlist |
Playlists matching a query |
/api/channel/{id} |
Channel details by ID |
/api/channel/handle/{handle} |
Channel details by @handle |
/api/channel/path |
Channel details by custom URL path |
/api/channel/{id}/videos |
A channel's videos |
/api/channel/{id}/shorts |
A channel's shorts |
/api/channel/{id}/live-streams |
A channel's live streams |
/api/video/{id} |
Video (or short) details |
/api/video/{id}/comments |
A video's comments |
/api/shorts/{id} |
Short details |
/api/playlist/{id}/videos |
A playlist's videos |
/api/hashtag/{tag} |
Videos under a hashtag |
/api/trending |
Trending videos, optionally by region |
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 · 207 lines · 151 tokens per session scan A 1ab521665676
youtube-api is a skill published in the GitHub repository fetcher-sh/fetcher-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 2,001 once invoked, about $0.0008 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 2026-09-01.
Other skills, from other repositories
phone
Use when the user wants phone-number intelligence (lookup, carrier, line type, SIM-swap / call-forwarding fraud signals), US/CA number provisioning (rent a phone number), or outbound AI voice calls (Bland.ai under the hood — schedule, confirm, follow-up). Pay per call in USDC.
t2000-env-gate
The cross-app env-validation contract — every app with ≥1 required env var validates at boot via a Zod schema and exposes values through a typed env proxy; raw process.env.X reads are banned outside the env module. Use when adding or renaming an environment variable, wiring up a new app in apps/, writing or reviewing…
vss-manage-video-io-storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams) and to provision a source and fan it out to a headless (no-agent) build's perception consumers (RT-CV/RT-Embed/RT-VLM). Not for VLM inference, semantic search, or agent-backed ingestion.
vss-deploy-detection-tracking-2d
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM…
vss-search-archive
Use this skill when a user wants to search archived VSS video or ingest or delete a source for search. Do not use it for visual Q&A, live captioning, or video summarization.
vss-query-analytics
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via VA-MCP (Docker :9901 or Kubernetes ${VSSPUBLICURL}/va-mcp). Not for live VLM or incident-range narrative reports.