MODE: ADVANCED

CLAUDE CODE PATTERNS

Seven battle-tested patterns from 2000+ hours of LLM development. Master the feedback loops that make AI reliable.

patterns_init.sh
$ ./load_patterns --source=production
# Core philosophy: YOU own the failures
# Either bad prompts or bad context
# Fix the system, not the symptoms
Ready. Select your module below.
CORE_PRINCIPLE

"Any issue in LLM-generated code is solely due to YOU, the user." Problems trace back to two root causes: inadequate prompt engineering or insufficient context management.

// The patterns below fix both. No more blaming the model.

// CORE_MODULES

// EXECUTABLE_SKILLS

PERFORMANCE_NOTE

Models degrade ~50% at 50k tokens. Context is finite. Every token must earn its place. These patterns help you stay lean and effective across long sessions.

// Treat context like RAM. Clean it. Manage it. Respect its limits.