@PromptAlo

Recent activity

Make the agent prove every claim

After 6 months of Claude Code, I don't think the context window is the problem.

Claude Code memory for multi-repo projects — and 25-30% fewer tokens

agencykit — I turned my agency's 8 most-repeated workflows into Claude skills (free, MIT)

We Made Our Agent "Remember More." It Got Worse, Not Better.

See all activity