What it does

This skill transforms your AI agent into a high-efficiency developer that prioritizes low latency and minimal token consumption. It enforces strict constraints to eliminate conversational filler, avoid redundant file reads, and optimize tool usage through batching and targeted search.

Why use this skill

Standard LLM behavior is often verbose, re-explaining logic or re-reading files unnecessarily. This "token tax" compounds into significant costs and slower response times. This skill replaces that behavior with a "decide and act" philosophy. It ensures your agent only reads what it needs, only writes what changed, and executes multiple commands in single tool calls to maximize throughput while minimizing your API bill.

Supported tools

• File System: Optimized with partial reads (sed/head) and grep-first workflows.
• Shell: Batching multiple bash commands and truncating noisy output.
• Editing: Strict use of minimal diffs and str_replace over full-file rewrites.