Opus 4.5 is not the normal AI agent experience that I have had thus far

Re:Opus 4.5 is not the normal AI agent experience that I hav... by edg5000 on Wednesday January 07, 2026 @07:48AM (#46525823)

This will work (if you add more details):

"Have an agent investiate issue X in modules Y and Z. The agent should place a report at ./doc/rework-xyz-overview.md with all locations that need refactoring. Once you have the report, have agents refactor 5 classes each in parallel. Each agent writes a terse report in ./doc/rework-xyz/ When they are all done, have another agent check all the work. When that agent reports everything is okay, perform a final check yourself"

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by gck1 on Wednesday January 07, 2026 @10:46AM (#46527707)

And you can automate all this so that it happens every time. I have an `/implement` command that is basically instructed to launch the agents and then do back and forth between them. Then there's a claude code hook that makes sure that all the agents, including the orchestrator and the agents spawned have respected their cycles - it's basically running `claude` with a prompt that tells it to read the plan file and see if the agents have done what they were expected in this cycle - gets executed automatically on each agent end.

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by edg5000 on Thursday January 08, 2026 @12:32AM (#46537569)

Interesting. Another thing I'll try is editing the system propmts. There are some projects floating around that can edit the minified JavaScript in the client. I also noticed that the "system tools" prompts take up ~5% context (10 ktok).

[ Parent | on HN ]