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-expertgit 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 | $0.00044 | $0.00438 |
| Opus 5 | $0.00022 | $0.00219 |
| Sonnet 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 2d 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
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.
- 2d 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 (241 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 438 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 2026-08-30.
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.