Writing Claude Directives

REQUIRED: Also apply ed3d-extending-claude:prompt-security-hardening when using this skill. Directives that demonstrate unsafe secrets handling teach agents to leak secrets.

Core Principles

1. Claude is smart. Only write what it doesn't already know. Challenge each line: does this justify its token cost?

2. Positive > Negative framing. "Don't do X" triggers thinking about X (pink elephant problem). Say what TO do, not what to avoid.

# Bad: triggers the behavior
Don't create duplicate files

# Good: directs to correct behavior
Update existing files in place

3. Context motivates compliance. Explain WHY, not just WHAT. Claude generalizes from motivation.