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 byadsco/meta-ads-mcp --skill meta-ads-video-analysisgit clone --depth 1 https://github.com/byadsco/meta-ads-mcpWrote 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/byadsco/meta-ads-mcp/meta-ads-video-analysis)<a href="https://agentmods.dev/skills/byadsco/meta-ads-mcp/meta-ads-video-analysis"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-video-analysis/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/byadsco/meta-ads-mcp/meta-ads-video-analysis"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-video-analysis.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 | $0.00097 | $0.01720 |
| Opus 5.5 | $0.00039 | $0.00688 |
| Sonnet 5.5 | $0.00019 | $0.00344 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
meta-ads-video-analysis 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 today.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing an ad video
A video ad cannot be judged from its poster frame. The first three seconds decide whether it is watched at all, and the retention curve says where attention is lost. This skill covers getting the video in front of a model, and reading it once it is there.
Which delivery do you need
Ask what your own model can ingest, then pick once. Getting this wrong wastes either money or the analysis.
| Your model | Call | Cost |
|---|---|---|
| Ingests video (Gemini CLI, agents on the Gemini API) | ads_get_video_media with delivery: "inline" |
none |
| Sees images (Claude, GPT, most others) | ads_get_video_media with delivery: "frames" |
none |
| Text only, or you want a written verdict on file | ads_analyze_video |
the tenant's Gemini quota, about 0.02 USD |
| You only need the link | delivery: "url" |
none |
inline embeds the MP4 as a resource blob, so a video-capable model watches the actual ad with no intermediary. It is measured in megabytes: up to 20 MiB per video over HTTP, and 6 MiB for the whole result over stdio (Claude Desktop, and Claude Code when it runs the server locally), because MCP SDK clients close the connection on a message above 10 MiB. The budget is about the transport, not the model; on those two clients the Claude models read images rather than video anyway, so use frames and never reach for inline by default.
frames extracts real keyframes with ffmpeg and returns them as image blocks. A contact sheet by default, which is the cheapest useful view; frame_layout: "individual" when timing matters; include_audio: true adds the audio track for a model that hears.
ads_analyze_video has the server watch it with Gemini and return structured JSON. Use it when your model cannot see the video at all, or when the team wants a written analysis to keep. It needs the tenant's own Gemini key.
Getting to the video
Your own ad: video_id, ad_id or creative_id. An ad or creative resolves every video in it, capped by max_videos; video_index picks one.
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.
- today Changed · +12 lines d79e05133693
- 1mo ago Changed 14519564aa40
- 1mo ago First seen · 81 lines · 97 tokens per session scan A 5773100f8a29
meta-ads-video-analysis is a skill published in the GitHub repository byadsco/meta-ads-mcp (24 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,720 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-18.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…