Tag
A tweet sharing best practices for AGENTS.md optimization and dead code cleanup, with ready-to-copy prompts. It covers use cases of cleaning up 800K+ lines of dead code with GPT-6 Astra + Codex, and optimizing CI duration with GPT-6.1 Sol.
Linear reworked their CI pipeline to address bottlenecks from AI coding, optimizing for speed and cost while scaling test coverage.