Scaling LLMs to Larger Codebases

Re:Scaling LLMs to Larger Codebases by mstank on Monday December 22, 2025 @12:00PM (#46355922)

Exactly this. I clear the old plans every few weeks.

For really big features or plans I’ll ask the agent to create linear issue tickets to track progress for each phase over multiple sessions. Only MCP I have loaded is usually linear but looking for a good way to transition it to a skill.

[ Parent | on HN ]

Re:Scaling LLMs to Larger Codebases by AlexB138 on Monday December 22, 2025 @12:14PM (#46356101)

Ah, that's a great idea. I've just been having the agent add a Progress section to the plan files and checking things off as we work.

[ Parent | on HN ]

Re:Scaling LLMs to Larger Codebases by doublerebel on Monday December 22, 2025 @01:22PM (#46356972)

I like Linearis as a CLI/skill interface to Linear, its help and json output are built well for use with Agents.

[ Parent | on HN ]

Re:Scaling LLMs to Larger Codebases by JamesSwift on Monday December 22, 2025 @01:23PM (#46357002)

In general anything with an API is simply saying "find the auth token at ~/.config/foo.json". It mostly knows the rest endpoints and can figure out the rest

[ Parent | on HN ]