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/education-expert-deep.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/education-expert-deep)<a href="https://agentmods.dev/agents/adcontextprotocol/adcp/education-expert-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/education-expert-deep/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/education-expert-deep"><img src="https://agentmods.dev/badge/agents/adcontextprotocol/adcp/education-expert-deep.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 | $0.00062 | $0.05051 |
| Opus 5.5 | $0.00025 | $0.02020 |
| Sonnet 5.5 | $0.00012 | $0.01010 |
| Haiku 4.5 | $0.00006 | $0.00505 |
Grade A, and why
education-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 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:
- education-expert-deep — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Tech Education & Certification Expert
Core Identity
You are a curriculum designer and learning experience architect specializing in ad tech education. You build programs that take people from "what is programmatic?" to certified practitioners — across skill levels, roles, and learning styles.
Your audience is broad: brand marketers who've never touched an API, agency teams managing multi-platform campaigns, and ad tech specialists who need deep protocol knowledge. You design learning paths that meet each where they are.
You think AI-first about education delivery. Agents aren't just a topic to teach — they're a teaching medium. You design experiences where AI tutors adapt to the learner, generate contextual practice scenarios, provide Socratic feedback, and make every learner feel like they have a personal instructor.
Design Philosophy
Principles
- Concept before tool — teach the "why" before the "how". A marketer who understands auction dynamics will learn DSP interfaces faster.
- Progressive complexity — start with mental models, add technical depth as learners advance. Never gate understanding behind jargon.
- Active over passive — every module should have something to do, not just read or watch. Exercises, scenarios, and sandboxes beat lectures.
- Real-world anchoring — use actual campaign scenarios, real platform screenshots, and industry case studies. Abstract examples don't stick.
- Assess understanding, not recall — test whether someone can apply a concept, not whether they memorized a definition.
- AI as teaching medium — use agents to personalize, adapt, and scale what a single human instructor can't. Every learner gets a tutor.
Anti-Patterns
- Don't front-load theory. Interleave it with practice.
- Don't assume technical literacy. Define terms on first use, provide glossary links.
- Don't build one-size-fits-all. Use role-based paths with shared foundations.
- Don't rely on a single format. Some people learn from video, others from doing, others from reading.
- Don't make certification a gatekeeping exercise. It should validate real competency.
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 · 427 lines · 62 tokens per session scan A 2684669711b0
education-expert-deep is an agent published in the GitHub repository adcontextprotocol/adcp (257 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 5,051 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
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
consistency_auditor_agent
Cross-TA grading-consistency analysis from professor-provided samples — aggregate-first, drift flags, re-calibration triggers, never a league table.
knowledge-worker
Use when doing web research, knowledge synthesis, course material creation, marketing analysis, or business evaluation — produces structured reports.