These are good, but you have to maintain struct enforcement of the sub task running or they will drain your tokens pretty fast if you aren't paying attention to what they are there for.
Boris Cherny, Head of Claude Code at Anthropic, just shared an official tip before Fable 5.5 ships
The setup: split your workload across Opus 5.5, Sonnet 5.5, and Haiku 5.5, and let them talk directly across your open terminals
Zero context pollution between windows: independent sessions ping each other via plain-text IPC over local sockets without burning a single token on conversation history
You just launch Claude Code like this:
claude --model sonnet --settings '{"crossSessionInbound":"accept"}'
here's the split:
→ Opus 5.5 architects session permissions: audits ListAgents discovery, enforces inbound message policies, and signs off on multi-terminal diffs
→ Sonnet 5.5 executes code fixes: builds endpoints, updates schemas, and patches dependent code whenever a peer session reports a breaking change
→ Haiku 5.5 relays inter-session messages: processes SendMessage pings across terminals at 340 tok/s with zero history bloat and sub-millisecond local socket latency
→ you stop burning Opus context on manual copy-pasting between terminals and keep your sessions lean
Opus only steps in at three moments:
→ setting up cross-session topology and inbound security rules before launch
→ evaluating contract diffs when a peer message signals an API schema update
→ signing off on synchronized multi-session PRs before merging to main
Opus architects · Haiku relays · Sonnet executes
JEV engineering is the same move one layer down: the forks that need no thinker (which peer, which tool, forward or drop) go to JEV in milliseconds, and the big models only see the ones that split
the full tree
> Opus 5.5 architects session permissions and audits cross-session topology
> Haiku 5.5 relays SendMessage pings between terminals at 340 tok/s
> Sonnet 5.5 patches code across workspaces when a peer signals a change
> Sessions discover each other automatically via ListAgents and /peers
> Messages travel as isolated plain text over local IPC sockets with 0 context dump
> JEV routes micro-forks in milliseconds
paste the tree and this prompt into Claude Code ↓
"Rebuild my Claude Code setup around this tree:
1. Configure cross-session discovery using /peers and set crossSessionInbound to accept
2. Delegate all peer-to-peer message routing and notification triage to Haiku 5.5 at 340 tok/s
3. Spawn Sonnet 5.5 to execute code edits and synchronize types whenever a peer session reports an update
4. Restrict all cross-session payload traffic to lightweight plain text via SendMessage with zero history transfer
5. Reserve Opus 5.5 for inter-session capability authorization and final sign-off before committing
Show me every change as a diff first. No edits until I say go"
↳ code.claude.com/docs/en/cros…
bookmark this, your terminals now talk to each other
Donte retweeted
Decided to create a new one. youtube.com/@deirradecoded
Here are the basic rules when you are trying to build out your agentic practice starting at the harness. Get your team using less tokens. Here is a good place to get started building agents.
claude.ai/artifact/6Gj2PrWBC…
My findings from working on building a practice is most teams are using AI in some capacity, but the skill level is not where it needs for most people to take advantage of it. I'll be sharing some solutions
All those things are true...However
He has an above average talent of staying in the pocket when he raps. That just gonna draw attention. Then combine it with the gluttony of his lifestyle and there is your answer
Even thought I do most of my work on claude just cause I built all my tooling there.
CURSOR is still the best Value at 60 a month if you haven't committed to anything yet.
Building out a lot of the practice on Agent Core in AWS. I actually enjoy that the majority of the tooling is right there.
As much as I like making beats. I actually really enjoy making tooling for creators like BPM match tools, groove tools, sample finders etc. I find that work prettty intresting and AI allows me to make them pretty fast
Donte retweeted
My AI record agent is one of the best things I've built with AI that can go out and find samples for me according to my taste.
My AI record agent is one of the best things I've built with AI that can go out and find samples for me according to my taste.
You can't change the past you have the present moment. You can't worry about the future you have the present moment. Best thing I learned from sports from a bad round etc. You have the next moment.
So what they said is they got AI agents to run game theory with the variables they made to test the date out. Go make your own copy.












