← Back to context Comment by jwolfe 13 hours ago This wastes both tokens and turns. But yes it's probably the best option we have today. 3 comments jwolfe Reply pishpash 13 hours ago It can try its own file and fall back to generic like here. What's wrong with that? recursivegirth 13 hours ago Wasting turns? That is silly, use a better harness. Also token usage can mitigated by incremental discovery instead of stuck 5k+ worth of tokens in the AGENT/Claude md file. jwolfe 13 hours ago Every turn means more tokens in ways that are not obvious to most people and lead to tons of unnecessary cache reads.No harness can batch your agents.md read with the reads the contents of the file tell it to read.
pishpash 13 hours ago It can try its own file and fall back to generic like here. What's wrong with that?
recursivegirth 13 hours ago Wasting turns? That is silly, use a better harness. Also token usage can mitigated by incremental discovery instead of stuck 5k+ worth of tokens in the AGENT/Claude md file. jwolfe 13 hours ago Every turn means more tokens in ways that are not obvious to most people and lead to tons of unnecessary cache reads.No harness can batch your agents.md read with the reads the contents of the file tell it to read.
jwolfe 13 hours ago Every turn means more tokens in ways that are not obvious to most people and lead to tons of unnecessary cache reads.No harness can batch your agents.md read with the reads the contents of the file tell it to read.
It can try its own file and fall back to generic like here. What's wrong with that?
Wasting turns? That is silly, use a better harness. Also token usage can mitigated by incremental discovery instead of stuck 5k+ worth of tokens in the AGENT/Claude md file.
Every turn means more tokens in ways that are not obvious to most people and lead to tons of unnecessary cache reads.
No harness can batch your agents.md read with the reads the contents of the file tell it to read.