Add AEO Foundations Architect

[hedonnn]

What does this PR do?

Adds a new AEO Foundations Architect agent to marketing/ — a specialist who builds the infrastructure layer that makes websites discoverable, parseable, and actionable by AI systems (crawlers, citation engines, and browsing agents).

While most AEO discussions focus on getting cited by ChatGPT or ranking in Perplexity, this agent works one level below: ensuring the prerequisites are in place before any of that can happen. It audits and implements robots.txt AI crawler directives, llms.txt discovery files, token-budgeted content, and structured content availability.

The approach reflects the current state of AEO infrastructure (2025-2026): llms.txt adoption is growing but pre-standard, AI crawler user agents are multiplying, and token budgets are becoming a real constraint as AI systems process web content.

Agent Information

• Agent Name: AEO Foundations Architect
• Category: marketing
• Specialty: AI Engine Optimization infrastructure — robots.txt, llms.txt, token budgets, content availability, agent discovery files

What makes this agent different

Most AEO agents focus on citations and rankings. This one focuses on the foundation layer that citations and rankings depend on. It produces:

1. An AEO Foundations Scorecard — a 12-point pass/fail audit across Discovery, Parsability, and Capability layers
2. Ready-to-deploy templates — robots.txt AI crawler configuration, llms.txt, token budget worksheets
3. A phased implementation plan — from zero-risk quick wins (Day 1-3: robots.txt) to strategic capability declarations (Day 21-30: agent-permissions.json)
4. A cross-wave prerequisite checklist — verifying that SEO (Wave 1), AI Citations (Wave 2), and Agentic Task Completion (Wave 3) all have their infrastructure in place

The agent is deliberately precise about spec maturity — it distinguishes between established standards and emerging conventions, and never overstates adoption.

Motivation

Teams routinely invest in AI citation optimization or agentic search while their robots.txt blocks every AI crawler and they have no machine-readable discovery files. The gap is infrastructure: the plumbing that must exist before any downstream AEO work can succeed.

This agent fills that gap with a structured audit-and-implement workflow that takes a site from "invisible to AI" to "foundation-ready" in 30 days.

Testing

Tested on SaaS, real estate, and service business websites. The scorecard format consistently surfaces blind spots that teams miss (most commonly: legacy robots.txt with no AI crawler rules, and content trapped behind JavaScript rendering). The phased implementation plan has been validated as actionable by non-technical site owners.

Checklist

• Follows agent template structure from CONTRIBUTING.md
• Includes YAML frontmatter with name, description, color, emoji, vibe
• Has concrete template examples (Scorecard, robots.txt, Token Budget, llms.txt)
• Includes personality and voice (infrastructure-first, checklist-driven, spec-maturity-aware)
• Defines success metrics (8 measurable outcomes)
• Includes step-by-step workflow (5 phases)
• Proofread and formatted correctly
• Tested in real scenarios

[bensl84]

Closing — this is my personal fork (bensl84/agency-agents). The canonical project lives at https://github.com/msitarzewski/agency-agents — please re-open your PR there. Thanks!