Splitting work by decision difficulty: Jev as reflexes, Opus only for judgment
With Jev at $0.042 per million tokens versus Opus at $4, small decisions like picking files, choosing tools, and retrying or stopping go to Jev, while the large model only handles genuinely hard decisions.
OPUS 5.5 SHOULD NEVER READ YOUR FILES OR DECIDE “RETRY OR STOP” $4 per million input tokens for Opus. $0.042 for Jev. same decision, 95x apart so split the job by what each decision actually needs: Jev: reflexes. which file, which tool, retry or stop. answers in milliseconds Haiku 5.5: eyes. reads and audits every file in parallel Sonnet 5.5: hands. writes each fix Opus 5.5: the head. writes the plan, judges what comes back the trap: a workflow agent runs on your session’s model unless something assigns another one. start Claude Code on Opus and every agent is Opus too the fix is two lines. put model: haiku in your scanner’s agent file and model: sonnet in your editor’s, both in .claude/agents/ claude --model opus --effort ultracode first run on a small slice (/config workflowSizeGuideline=small). with ultracode on, the “Large workflow” warning doesn’t show, so watch /workflows while it runs the biggest model should only see the decisions that are actually hard
This post quotes another post: x.com/rvaniaaaa/status/2109385796751114346