Annie Tunturi db19741bee Update subagent model selection guidance
- Use kimi-k2.5 for opus-level tasks
- Use nemotron-3-super for sonnet-level tasks
- Use kimi-k2-thinking for deep reasoning at flash end
- Document what NOT to use (qwen, claude,)

Signed: Annie Tunturi <ani@wiuf.net>

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta Code <noreply@letta.com>
2026-03-20 22:51:52 -04:00
Description
"From each according to their updates, to each according to their needs"
MIT 288 MiB
Languages
Go 62.6%
TypeScript 34%
Shell 2.1%
PLpgSQL 0.7%
Dockerfile 0.3%
Other 0.1%