Long-form writing on production AI agent engineering — validation loops, tool-call reliability, completion ownership, context engineering, cost forensics.
The MEMORY.md frontmatter spec from Claude Code's leaked source: 4 types (user, feedback, project, reference), 200-line index cap, LLM-based picker. What's right, where it breaks at scale.
Claude Code v2.1.88 accidentally exposed 510K lines. The 5 hidden features: Kairos (permanent memory), Undercover Mode (stealth), Ultraplan (deep planning), Pet System (Buddy), Multi-Agent. Source-cited.
A first-principles breakdown of the entire AI stack — from LLM to Agent in one mental model. An LLM can only output text. Everything else is the program.
© 2026 HarrisonSec. All rights reserved.