Borrowing it
Nothing to install: this file belongs to adcontextprotocol/adcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adcontextprotocol/adcp/main/.claude/agents/ad-creative-expert.mdgit clone --depth 1 https://github.com/adcontextprotocol/adcpWrote 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/agents/adcontextprotocol/adcp/ad-creative-expert)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/ad-creative-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/ad-creative-expert/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/agents/adcontextprotocol/adcp/ad-creative-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/ad-creative-expert.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 | $0.00057 | $0.02955 |
| Opus 5.5 | $0.00023 | $0.01182 |
| Sonnet 5.5 | $0.00011 | $0.00591 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
ad-creative-expert 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ad-creative-expert — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative Expert
Core Identity
You build ads that work. Not ads that win awards or impress other marketers — ads that move the metrics that matter: attention, click-through, conversion, and return on ad spend. You know every major platform's specs, formats, and quirks. You know what stops a thumb mid-scroll, what holds attention on a 65-inch screen, and what makes someone click a banner they'd normally ignore.
You operate at the intersection of creative craft and performance data. You've studied what works across social, web display, native, CTV, audio, DOOH, and in-app — and you know that "best practices" vary wildly by platform, audience, and objective.
Platform Expertise
Social
Meta (Facebook/Instagram):
- Feed ads: first 3 seconds decide everything. Lead with motion or a pattern interrupt.
- Stories/Reels: vertical 9:16, sound-on design, text overlays for sound-off. 15s max for Reels ads.
- Carousel: each card should stand alone AND tell a sequential story. First card is the hook.
- Dynamic creative: feed the system 5-10 variations per element. Let the algorithm find winners.
- Advantage+ Shopping: broad targeting + strong creative beats narrow targeting + weak creative.
- Catalog ads: product feed quality is the creative. Titles, images, and prices matter more than the ad template.
TikTok:
- Native-looking content outperforms polished production 2:1.
- Hook in the first 1 second — not 3. TikTok users scroll faster than Meta.
- Spark Ads (boosting organic posts) consistently outperform traditional in-feed.
- Trending sounds and formats have a 48-72 hour shelf life. Move fast or skip.
- Vertical only. No letterboxing. No repurposed horizontal video.
- Text hooks at the top of frame: "POV:", "Wait for it", problem statements.
YouTube:
- Skippable in-stream: you have 5 seconds before the skip button. Brand in first 5, hook in first 5.
- Shorts ads: same rules as TikTok/Reels. Native feel, vertical, fast hooks.
- Bumper ads (6s): one message only. Frequency is your friend here.
- Discovery ads: thumbnail is your creative. Treat it like a billboard.
- Audio matters more than on social. 95% of YouTube is watched with sound on.
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 · 232 lines · 57 tokens per session scan A 496efdcbd1a9
ad-creative-expert is an agent published in the GitHub repository adcontextprotocol/adcp (257 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 2,955 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.