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 divinevideo/divine-mobile --skill vine-oembed-metadata-recoverygit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/vine-oembed-metadata-recovery)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/vine-oembed-metadata-recovery"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/vine-oembed-metadata-recovery/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/divinevideo/divine-mobile/vine-oembed-metadata-recovery"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/vine-oembed-metadata-recovery.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 | $0.00133 | $0.01173 |
| Opus 5.5 | $0.00053 | $0.00469 |
| Sonnet 5.5 | $0.00027 | $0.00235 |
| Haiku 4.5 | $0.00013 | $0.00117 |
Grade C, and why
vine-oembed-metadata-recovery scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://vine.co/oembed.json?url=https://vine.co/v/iLrDJJWn9e6" | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.get(url, timeout=10) How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vine oEmbed Metadata Recovery
Problem
Vine.co pages no longer render content — the SPA shell loads but the backend API
(archive-api.vineapp.com) returns 404, so pages just show a loading spinner. However,
the oembed endpoint is still live and returns structured metadata for any valid Vine URL.
Context / Trigger Conditions
- You have Vine URLs in the format
vine.co/v/{shortcode} - The Vine page shows only a loading spinner (SPA shell loads, API calls fail)
archive-api.vineapp.com/timelines/posts/s/{shortcode}returns 404- You need to identify which creator made a specific Vine
- You need to map Vine shortcodes to Vine user IDs
Solution
Single Lookup
Query the oembed endpoint:
GET https://vine.co/oembed.json?url=https://vine.co/v/{SHORTCODE}
Response Fields
The oembed response provides:
author_name— Vine username (e.g., "Kenrealdihboss")author_url— Profile URL containing the Vine user ID (e.g.,https://vine.co/u/1306031740015583232)title— Post description/captionthumbnail_url— 480x480 thumbnail (may still resolve on Vine CDN)thumbnail_width/thumbnail_height— Always 480x480width/height— Embed dimensions (600x600)html— Iframe embed codeprovider_name— "Vine"type— "video"version— "1.0"cache_age— Cache duration in seconds
Extract User ID
The Vine numeric user ID is in the author_url path:
author_url: "https://vine.co/u/1306031740015583232"
→ user_id: 1306031740015583232
Bulk Recovery Pattern
If you have a list of Vine shortcodes (from Wayback CDX crawls, social media embeds, etc.):
import requests
import time
def get_vine_oembed(shortcode):
url = f"https://vine.co/oembed.json?url=https://vine.co/v/{shortcode}"
resp = requests.get(url, timeout=10)
if resp.status_code == 200:
data = resp.json()
user_id = data.get("author_url", "").split("/u/")[-1]
return {
"shortcode": shortcode,
"username": data.get("author_name"),
"user_id": user_id,
"title": data.get("title"),
"thumbnail_url": data.get("thumbnail_url"),
}
return None
# Rate-limit to be respectful
for shortcode in shortcodes:
result = get_vine_oembed(shortcode)
if result:
print(f"{result['shortcode']} → {result['username']} (ID: {result['user_id']})")
time.sleep(0.5)
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.
- 1mo ago First seen · 117 lines · 133 tokens per session scan C 916d2b80c3ff
vine-oembed-metadata-recovery is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 133 tokens to every session and 1,173 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…