Agent Engineering Principles

Battle-tested principles for AI coding agents that produce reliable, high-quality work.

When to Use This Skill

• Writing or reviewing an AGENTS.md / CLAUDE.md / CURSOR.md file for a project
• Configuring a new AI coding agent or subagent
• Diagnosing why an agent keeps making the same mistakes
• Reviewing agent output quality and identifying systemic issues
• Onboarding an agent to a complex codebase

1. Plan Mode Default

• Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
• If something goes sideways, STOP and re-plan immediately — don't keep pushing
• Use plan mode for verification steps, not just building
• Write detailed specs upfront to reduce ambiguity