Token Efficiency

Name

han-core:token-efficiency

Description

Minimize token consumption without sacrificing quality. Every token spent on overhead is a token not available for thinking.

File Operations

• Use Edit for modifications — sends only the diff (~50-100 tokens), not the whole file
• Use Write only for new files — full file content costs ~500-5000 tokens
• Never re-read a file you just wrote — you already know its contents
• Batch related edits to the same file in one Edit call

Search Operations