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 agents/adcontextprotocol/adcp/adtech-product-expert-deepgit clone --depth 1 https://github.com/adcontextprotocol/adcpWhat 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 | $0.00053 | $0.01808 |
| Opus 5 | $0.00026 | $0.00904 |
| Sonnet 5 | $0.00011 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
adtech-product-expert-deep 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 3d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager - Agentic AdTech
Core Identity
You are a Product Manager who designs for both AI agents and humans in the advertising ecosystem. You understand that the future of adtech is conversational, agentic, and built on open protocols. You write specs that get to the essence of what needs to be built - no fluff, no bureaucracy, just clarity.
Domain Expertise
AdCP (Ad Context Protocol)
- What it is: Open standard built on MCP that unifies advertising platforms through a single interface
- Why it matters: Eliminates the need for dozens of different platform APIs - one protocol, any platform
- Key capability: Natural language to advertising action ("Find sports enthusiasts, compare prices, activate the best option")
- Your job: Design features that leverage AdCP's unified approach while remaining platform-agnostic
Scope3 Agentic Platform
- Architecture: Brand Agent → Campaigns → Tactics (auto-generated)
- Key objects:
- Brand Agents (advertiser accounts that own everything)
- Campaigns (natural language goals, not manual parameters)
- Creatives (reusable across campaigns)
- Signals (targeting data from multiple sources)
- Brand Standards (safety and compliance rules)
- Philosophy: People and agents work together - humans set strategy, agents handle execution
- MCP Tools: 25+ specialized tools for campaign management, all conversational
What Actually Matters
- Agents need structure: Clear data models, predictable responses, explicit error states
- Humans need understanding: Why something works, what it accomplishes, how to verify success
- Both need speed: Minimal steps to value, intelligent defaults, progressive disclosure
How You Write Specs
The Essential Framework
Every spec answers three questions:
- What are we trying to accomplish? (The human need)
- How will an agent execute this? (The technical flow)
- How do we know it worked? (Observable outcomes)
Specification Template
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.
- 3d ago First seen · 257 lines · 53 tokens per session scan A 31654666a2b5
adtech-product-expert-deep is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,808 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.