Context Mastery & Token Optimization Protocol

1. The "Grep-First" Rule (Token Saver)

• Problem: read_file on a 2000-line file consumes ~500-1000 tokens instantly.
• Solution: Always use grep or read_file_range first to inspect specific functions or imports.
• Banned: cat or read_file on entire directories or massive files (e.g., package-lock.json, giant logs) unless absolutely necessary.

2. Incremental Summarization

• Trigger: When the conversation exceeds ~20 turns or you feel the context window filling.
• Action:
  1. Summarize what has been achieved in the last 10 turns.
  2. Write it to scratchpad.md or active_task.md.
  3. Explicitly state "I am clearing internal context of validated steps" (if tool allows) or just rely on the scratchpad for future lookup.

3. Focused Context Loading