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 HYPD-AI/ads-mcp-plugin --skill hypd-overviewgit clone --depth 1 https://github.com/HYPD-AI/ads-mcp-pluginWrote 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/hypd-ai/ads-mcp-plugin/hypd-overview)<a href="https://agentmods.dev/skills/hypd-ai/ads-mcp-plugin/hypd-overview"><img src="https://agentmods.dev/badge/skills/hypd-ai/ads-mcp-plugin/hypd-overview.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00313 |
| Opus 5 | $0.00019 | $0.00156 |
| Sonnet 5 | $0.00008 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
hypd-overview 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 6d 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.
What it actually says
What HYPD can do
HYPD analyzes the user's real advertising data, read-only: it never changes campaigns, budgets or ads.
Platforms: Google Ads · Meta (Facebook) Ads + Ad Library · Google Analytics (GA4) · Merchant Center — plus keyword research, competitor/SERP/Shopping research, and landing-page checks.
Slash commands (namespace hypd-ai-ads):
| Command | What it does |
|---|---|
/audit |
full Google Ads account audit |
/wasted-spend |
find wasted spend, with the money behind each finding |
/negatives |
negative-keyword candidates from search terms |
/keywords |
keyword research, new campaign or expansion |
/feed-audit |
Merchant Center feed quality |
/meta-audit |
Meta Ads audit, ecom or lead-gen |
/creative |
creative analysis, own or competitor |
/attribution |
GA4 Data-Driven vs Last-Click comparison |
/landing-page |
technical landing-page audit |
/report |
client-ready monthly report |
/prompts |
browse the full prompt library (87+) |
Anything else: just ask in plain language — HYPD's server routes to the right internal skill automatically.
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.
- 6d ago First seen · 28 lines · 39 tokens per session scan A c5cdb6e7eb44
hypd-overview is a skill published in the GitHub repository HYPD-AI/ads-mcp-plugin (2 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 313 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
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
analyze
Pull ad campaign performance data from connected platforms. Use when the user asks about campaign results, ROAS, ad spend, CTR, conversions, search terms, negative keywords, ad fatigue, budget pacing, delivery issues, or wants to diagnose why ads aren't spending. Also use for Google search term reports and keyword…
launch
Launch ad campaigns on connected platforms. Use when the user wants to create a new campaign, set up targeting, configure ads, upload media, duplicate campaigns, or go live with new ads. All creations produce drafts that require explicit user approval before publishing. Not for performance analysis, competitor…
studio
Generate AI ad creatives — images, copy, and briefs. Use when the user wants to generate ad images, create ad creatives with AI, make an ad, build a creative brief, clone a competitor ad, resize creatives for different placements, or edit existing images. Also use when the user mentions "AI ad generation", "ad…
spy
Research competitor ads using the ad library. Use when the user wants to spy on competitor ads, see what ads a brand is running, browse competitor creatives, find top-performing ads, or do ad library research. Also use when the user mentions "ad library", "what ads is X running", "competitor creatives", or wants to…
setup
Connect ad platforms to AdKit. Use when the user wants to set up AdKit, link their Meta, Google, or TikTok ad accounts, or verify their connection. Not for campaign creation, performance analysis, or ad library browsing — use the launch or analyze skills for those.