| ▲ | a_c 2 hours ago |
| Every subagent send the same ~30k system prompts. If you are using fable/opus, that's easily 30% of a 5-hour window for 7 subagent, before doing any work |
|
| ▲ | micw 2 hours ago | parent | next [-] |
| I recently did a few tests. And always the same prompt has been cached properly. |
| |
| ▲ | ricardobeat an hour ago | parent [-] | | Cache is usually not shared between agents - they can have different base prompts, tools, and be an entirely different model. |
|
|
| ▲ | megous 2 hours ago | parent | prev [-] |
| If it's always the same prompt, can't they have it pre-cached globally for all? |
| |
| ▲ | a_c 34 minutes ago | parent | next [-] | | The system behaviour is totally up to anthropic's discretion. Its current behaviour is verifiable. In claude code, spawn a subagent with 1. Agent("Test") 2. look at your token usage 3. Repeat a few times I didn't check again as I type this message but am somewhat sure subagent doesn't cache system prompt as of maybe last week | |
| ▲ | erikus 2 hours ago | parent | prev [-] | | I'm pretty sure the system instructions are a function of your environment and not the same universally. That said, there should be a finite number of branches so still cacheable. |
|
