Quick BuilderCore / agent-system update. I’ve been quiet for a while because I’ve been deep in the worker-runtime layer. The biggest lesson so far is that the hard part is not just “getting agents to do work”. The hard part is governing them properly. Over the last 10–15 worker-runtime milestones I’ve been building out the foundations for: - model registries - worker identity policies - routing policy - review/judge/operator separation - API cost awareness - premium model gating - OpenAI / Claude provider separation - Fable 5 added as an inert premium model profile - evidence-linked worker chains - controlled ingestion gates - reviewer/judge frozenset policy - no self-review / no self-judgment boundaries One of the biggest things I’ve learnt is that API cost changes the architecture. You cannot just let a system “pick the best model” freely, because the best model may also be the most expensive one. So BuilderCore now needs to think in terms of: - cheapest sufficient model - risk-based routing - premium model approval - per-call cost caps - per-ticket cost caps - token tracking - worker performance history - when a model is allowed to be used - when a model is only catalogue-aware but not live-enabled For example, Fable 5 may be extremely powerful, but it is too expensive and too high-risk to make default. So I added it as an inert premium profile first: BuilderCore knows it exists, knows it is premium, but cannot dispatch it yet until premium gates and usage governor are ready. That is the kind of architecture decision I’m learning matters. The other big lesson is identity separation. A model is not the same thing as a worker identity. For example: - claude-code is a tool identity - codex-implementer is a provider worker identity - claude-sonnet-4-6 is both a model identity and a reviewer identity in the current court chain - human/operator remains the final authority This matters because if the system confuses models with identities, it can accidentally allow the wrong worker to review or judge its own work.

I am kicking off my weekly planning workflow for next week. At the start of last school holidays, this was a brand new system and I was just moving from a set of saved prompts and skills to ICM. (Hey, it’s been an 11 week term - in ICM time, that’s a few lifetimes!) So, to say I had a little bit of trepidation was an understatement. I have to say every week when I kick this stage off in desktop (I am currently on NotePlan - the connector only works on Desktop) it makes me happy to see Claude go in and say “this is a well-structured system”. Honestly, every week, and I still get the warm fuzzies. I’d done extra context set up and everything. And I knew I already had school holiday templates… Turns out Mira back in April had taken the time to put in a holiday mode to the system. Did I remember this? No, not at all. Did my system make sure that Claude had everything and it went smoothly? Of course it did. Honestly, thank you past me. I didn’t even remember the skill’s holiday mode and my *goodness* does that make my life easier for the next 3 weeks.