Holy sh*t, someone just open-sourced most ground breaking thing. everyone has posted this format so I will to telling you exactly how to use it. and I am going to tell you about the best repositories that nobody is talking about (except everyone is talking about them). How does this work: I copy past other posts into my claude, and it auto sends for me. Here is a useless image to peak your interest
@theo What habits do you suggest to help with carpal tunnel? I tried ergonomic keyboards, but I don't love them. I'd rather have a consistent keyboard format across all my different workspaces
holy f*ck. Official Anthropic tip for Claude Code: stop running agent teams on Opus and Sonnet 5.5 alone when Haiku 5.5 can swarm the bus at 340 tok/s
spin up an autonomous team with /teams
claude --teammate-mode auto
Opus 5.5 acts as the lead architect, scoping architecture and validating pull requests
Sonnet 5.5 teammates take isolated git worktrees and hammer out implementations at medium effort
Haiku 5.5 swarms the peer-to-peer bus as a dedicated scout and fuzzer, only stepping in at three critical moments:
โ before a contract locks: does the frontend payload match the backend schema?
โ when a test breaks twice: are we patching the bug or just hiding the symptom?
โ before calling done: what attack surface or edge race did everyone overlook?
Sonnet 5.5 builds. Haiku 5.5 swarms. Opus 5.5 merges and ships
Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge
Plan on high. Delegate on medium. Keep Haiku 5.5 on P2P call.
- the full team setup
> Opus 5.5 on high coordinates the session and synthesizes PRs
> teammate-ux builds client state inside a separate git worktree
> teammate-back writes endpoints and handles Redis atomic locks
> teammate-scout runs invariant fuzzing and AST parsing on Haiku 5.5 at 340 tok/s
> all teammates communicate directly over peer-to-peer messaging without coordinator drag
> tasks.json manages file-level mutex locks so nobody steps on another worktree
paste the setup and this prompt into Claude Code below:
"Configure my Claude Code workspace for autonomous agent teams:
1. Enable experimental agent teams in ~/.claude/settings.json:
> Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to 1 in env block
> Set teammateMode to auto
> Pin main lead model: opus with effortLevel: high
2. Audit ~/.claude/agents and create teammate profiles fitting ux, backend, and scout:
> teammate-ux: model: sonnet, effort: medium, isolation: worktree
> teammate-back: model: sonnet, effort: medium, isolation: worktree
> teammate-scout: model: haiku, tools: Read, Grep, Glob, SendMessage
3. Configure shared task coordination in ~/.claude/CLAUDE.md:
> Initialize tasks.json for task dependencies and atomic file mutexes
> Teammates resolve contracts directly over peer-to-peer messaging without lead intervention
> Enforce Haiku scout schema verification before teammates mark tasks completed
4. Quality gate:
> Opus lead reviews synthesized worktree diffs and validates test suites before final merge
Show every configuration diff first. Do not apply edits until confirmed"
โณ
https://t.co/M2gSWKYxqH