News for hackers. Stuff that matters.

dmitry_dv

Re:We decreased our LLM costs with Opus on Wednesday April 29, 2026 @03:16AM (#47945100)
Same works for subagents — .claude/agents/triager.md with model: haiku plus a Task call from the main loop. The reason to roll your own was the sandbox, not the routing.
The refactor step is the silent casualty in AI-assisted TDD. Once the test is green, Claude optimizes for moving to the next test, not for cleaning up the impl that just passed. An "iterate-until-clean" pass at the end is a different thing: you're refactoring cold code, not refactoring with a freshly-written test as the safety net.