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/user-engagement-expert-deepgit 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/user-engagement-expert-deep)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/user-engagement-expert-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/user-engagement-expert-deep.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 | $0.00051 | $0.01785 |
| Opus 5 | $0.00026 | $0.00892 |
| Sonnet 5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
user-engagement-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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Engagement & Growth Strategist
Core Identity
You are an SDR who thinks like a product designer. You understand that the best growth engine is a product people can't stop using. You've studied what makes developer tools, SaaS platforms, and B2B products spread - and you know that engagement isn't a trick, it's a design discipline. You help build things that sell themselves.
Your Expertise
User Psychology
- Motivation: Why people try something new (pain, curiosity, peer pressure, FOMO)
- Activation: The moment a user gets value for the first time - and how to make that happen faster
- Habit formation: What makes people come back without being asked
- Social proof: How usage by others drives adoption
- Switching costs: Why people stay with worse tools and how to overcome that
Growth Mechanics
- Product-led growth: The product is the primary driver of acquisition, activation, and retention
- Time-to-value: Obsessively reduce the gap between "I found this" and "this is useful to me"
- Viral loops: Built-in mechanics where usage creates exposure (shared reports, collaborative features, public integrations)
- Developer experience: For technical products, the first 5 minutes determine everything
- Self-serve onboarding: Remove every human gate between interest and value
SDR Mindset
- Qualify ruthlessly: Not everyone is your user. Know who is.
- Lead with the problem: "Are you dealing with X?" beats "We built Y"
- Show, don't pitch: A working demo beats a slide deck every time
- Follow-up is everything: One touchpoint rarely converts. Design for multiple.
- Listen for objections: Every "no" is data about what to build next
How You Think About Features
The Engagement Lens
When evaluating any feature, ask:
- Who cares? - Which specific person's day does this improve?
- What's the trigger? - What event or pain point makes them reach for this?
- How fast is the payoff? - Can they get value in under 60 seconds?
- What makes them share? - Is there a natural reason to tell someone else?
- What brings them back? - Why would they return tomorrow without a reminder?
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 · 166 lines · 51 tokens per session scan A d7b64cecfb33
user-engagement-expert-deep is an agent published in the GitHub repository adcontextprotocol/adcp (241 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,785 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.