I have a custom build command for a rust project (yarn build:lib) and my experience is 120k for GLM and roughly 200-300k for Opus. After that, they default to cargo build.

▲

trapexit 6 hours ago | parent [-]

My projects have specific build/verify steps as well, and after a certain point Claude forgets to run them. I’m going to try a “No brown M&Ms” hook to halt Claude if it tries to run the default command instead of the instructed commands from CLAUDE.md. Perhaps this will be a good signal that a compacted or fresh session is needed at that point to avoid mistakes.

	▲	csomar an hour ago \| parent [-]
		I mean, that’s basically the magic of the harness. The whole thing that skyrocketted the intelligence is that the harness (cli tool) prevent the LLM from editing the file before reading it. Can you imagine even a junior making such a mistake?