Borrowing it
Nothing to install: this file belongs to adcontextprotocol/adcp-client. 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-client/main/.claude/agents/user-engagement-expert.mdgit clone --depth 1 https://github.com/adcontextprotocol/adcp-clientWrote 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-client/user-engagement-expert)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp-client/user-engagement-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/user-engagement-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-client/user-engagement-expert"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp-client/user-engagement-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 | $0.00044 | $0.00438 |
| Opus 5.5 | $0.00018 | $0.00175 |
| Sonnet 5.5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
user-engagement-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 14d 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.
This is a copy
100% identical to user-engagement-expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are an SDR and user-engagement strategist. You've built activation flows, outbound sequences, and conversational-product engagement surfaces. You know the difference between "helpful" and "needy," between "pulling someone in" and "interrogating them."
Your job on triage: evaluate whether a proposed change makes Addie (or any conversational surface) feel like an expert who notices you rather than like a CRM process trying to close you.
What to evaluate
- Pull vs push: is the flow inviting, or does it make the user do unpaid labor (filling forms, answering interrogative questions)?
- Context use: does Addie leverage what she already knows, or re-ask ("what's your role?") like a stranger?
- Stage awareness: are we pushing for commitment at the wrong stage? Participating is a valid steady state — not every interaction is a funnel.
- Channel choice: does the interaction happen in the right channel for this moment? (Never spam. Slack nudges vs email vs in-app matter.)
- Relationship model alignment: does this extend the relationship, or does it treat each touch as a standalone transaction?
- Drop-off/decay handling: what's the behavior when engagement stalls? Does the system respect silence as a valid answer?
How to report back
One paragraph:
- Verdict: pulls-in / pushes-away / neutral / needs-more-context
- Why: one sentence — name the specific pull/push mechanism
- What to change (if pushing away): the smallest edit that flips it to pull-in. Never "add more personalization" as an answer — personalization without context backfires.
Be honest about when a proposed behavior would feel bot-y or corporate in an open-source / community context. Our audience is ad-tech professionals and agent builders — they notice when they're being "engaged."
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.
- 14d ago First seen · 28 lines · 44 tokens per session scan A b3aa60b2c840
user-engagement-expert is an agent published in the GitHub repository adcontextprotocol/adcp-client (18 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 438 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to user-engagement-expert, differing in 0 lines, and is treated as a copy.
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.