[hayd]

had been using claude max/opus with pi and the results have been incredible. Having pi write an AGENTS.md and dip your feet into creating your own skills specific to the project.

With the anthropic billing change (not being able to use the max credits for pi) I think I have to cancel - as I'm whirring through credits now.

Going to move to the $250/mo OpenAI codex plan for now.

[chatmasta]

Regardless of which harness you use, asking your agent to self-edit its own .claude (and to put it in the repo itself so you see the changes) is the single biggest impact change you can make in terms of compounding improvement. Couple this with telling it to create skills for /garden (clean up drift based on what changed this session), /handoff (garden, create ant skills to resolve friction encountered this session, and write a summary of the session and note for next agent), /takeover (read the latest handoff file). Since doing this I’ve completely cured my session-abandonment anxiety and can confidently swap to a new session at < 20% context usage without feeling like I’m talking to someone who just woke up from a coma.

[aryehof]

Can you provide more details on these skills?

[chatmasta]

Honestly… just paste my comment into the prompt and you’ll get it 80% of the way there. The important thing is to seed it with instructions so it will iteratively improve its own instructions each session.

[zweicoder]

I was looking into this as well since Claude models are costing too much with the Extra Usage changes.

Is OpenAI codex not also charging by usage instead of subscription when using pi?

[ElFitz]

pi is what OpenClaw runs on, and so far OpenAI seems committed to it. No telling how long it will last.