Making AI Coding Agents More Efficient: My Local Toolkit

A developer, Ammar Najjar, shares his local toolkit for making AI coding agents more efficient, focusing on controlling information flow rather than adding capabilities. He documents tools like Headroom, RTK, Caveman, Serena, rg, fd, ast-grep, jq, and yq, and explains how he defines their responsibilities in AGENTS.md to give agents the smallest amount of information necessary for correct decisions.

Giving AI coding agents more tools doesn’t necessarily make them more efficient. After using OpenCode and Claude Code heavily, I started focusing less on adding capabilities and more on controlling the information flowing into the agent. That means: I’ve documented the toolkit I currently use, including Headroom, RTK, Caveman, Serena, rg , fd , ast-grep , jq , yq , and others, along with how I define their responsibilities in AGENTS.md . The principle behind all of it is simple: Give the agent the smallest amount of information necessary to make the next correct decision. Full post: https://ammar-najjar.com/blog/local-ai-coding-toolkit/ https://ammar-najjar.com/blog/local-ai-coding-toolkit/