datavorous/prime-agent ? reverse-engineered prompt
Reverse engineered prompt
Build me a coding agent that can keep working for a long time without losing context. I want it to run in the current project folder, let me talk to it from a terminal, and have it edit files, run commands, and keep track of what it is doing. It should be able to spawn helper agents for separate tasks, come back to them later, and keep running in the background even if I disconnect.
I also want a simple way to set goals, pause and resume sessions, and review progress. If the agent learns something useful during the work, it should be able to save that as reusable memory or a skill for later. Make it work well for coding and research tasks, and include a way to run it autonomously with limits so it does not go off forever. If you need to look up current docs online, go ahead.
Are you gonna build this?
make sure you review the code using arcumet