WHAT NEW IN X10.31 SAT

AI collections from X · 22 collections · 61,986 posts

jevVIDEO

Opus writes the script, cheaper agents execute it

Opus 5.5 only writes the workflow script, Haiku scans and Sonnet patches, and micro-forks that need no thinking, such as picking files or retrying versus stopping, are routed to Jev in milliseconds.

Callan
@callanxaiArchived 13 days agoOriginally posted 2026.10.17
Callan @callanxaiOriginally posted 2026.10.17
Open original on X

THIS IS AN ABSOLUTE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: Opus 5.5 writes the entire plan as a script, and a swarm of cheaper agents executes it. Bigger jobs and far fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just start Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only steps in at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ http://code.claude.com/docs/en/workflows save it, you'll reach for it on every big task.

This post quotes another post: x.com/hanakoxbt/status/2110067711363457244

x.com/callanxai/status/2111195719927521372Archived 2026.10.17 10:05