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 agentmods add skills/agentproto/ts/youtubenpx skills add agentproto/ts --skill youtubegit clone --depth 1 https://github.com/agentproto/tsWhat 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 | $0.00045 | $0.01006 |
| Opus 5 | $0.00023 | $0.00503 |
| Sonnet 5 | $0.00009 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
youtube scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube — recon plan (InnerTube API)
Internal API: InnerTube —
POST https://www.youtube.com/youtubei/v1/<endpoint>?key=<INNERTUBE_API_KEY>&prettyPrint=false,
body { context: <INNERTUBE_CONTEXT>, ...params }. The web app uses this for
everything.
Config + auth (from the page)
INNERTUBE_API_KEY+INNERTUBE_CONTEXTlive inytcfg. Read in-page:;() => ({ key: ytcfg.get("INNERTUBE_API_KEY"), ctx: ytcfg.get("INNERTUBE_CONTEXT"), })- Public reads: often work with just key + context (no auth).
- Personalized / write (subscriptions, comments, like): need SAPISIDHASH
auth:
Authorization: SAPISIDHASH <ts>_<SHA1(ts + " " + SAPISID + " " + origin)>where SAPISID = theSAPISID(or__Secure-3PAPISID) cookie, origin =https://www.youtube.com, ts = unix seconds. Compute SHA-1 in-page (SubtleCrypto). Also sendX-Goog-AuthUser: 0,Origin, cookies (auto).
In-page fetch:
;async (endpoint, body) => {
const key = ytcfg.get("INNERTUBE_API_KEY")
const r = await fetch(
`/youtubei/v1/${endpoint}?key=${key}&prettyPrint=false`,
{
method: "POST",
headers: {
"content-type": "application/json" /* + SAPISIDHASH for writes */,
},
body: JSON.stringify({
context: ytcfg.get("INNERTUBE_CONTEXT"),
...body,
}),
}
)
return await r.json()
}
Endpoints to test
| Purpose | endpoint | params |
|---|---|---|
| Channel / home / playlist | browse |
browseId (channel UC…), params |
| Watch page → video + comments token | next |
videoId |
| Comments (+ who/likes) | next (continuation token from the watch next) |
continuation |
| Search | search |
query, params |
| Video metadata | player |
videoId |
| WRITE: comment | comment/create_comment / create_comment_reply |
createCommentParams |
| WRITE: like/dislike | like/like / like/dislike / like/removelike |
target.videoId |
| WRITE: subscribe | subscription/subscribe / unsubscribe |
channelIds |
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 First seen · 99 lines · 45 tokens per session scan A 7bd735deaf3b
youtube is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,006 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 2026-08-31.
Other skills, from other repositories
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.
goplaces
Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.
ai-browser-use
业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。.
docs-planner
Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…
pr-feedback
Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…