OPUS 5.5 SHOULDN'T BE DOING THE WORK. It should... be writing the PLAN. Claude Code workflows let Opus write a script that runs a whole swarm of agents in the background. Opus plans. Haiku 5.5 scans every file in parallel. Sonnet 5.5 makes the fixes. A verifier checks every finding. Opus only sees what survives. Your expensive model never reads 100 agent transcripts again. Setup prompt below 👇show more

it's f*cking insane.. Anthropic just dropped a Claude Code... setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this yearshow more

By tomorrow, everyone will be using this: Anthropic just... revealed the ultimate power move for Claude Code The concept: have Opus 5.5 design the master plan as a script, then deploy parallel swarms of the new Haiku 5.5 Massive scale operations with zero wasted Opus compute: the script manages the execution loop so Opus only reviews the final diff Simply boot up Claude Code with these parameters: claude --model opus --effort ultracode Here is the task distribution: -> Opus 5.5 translates your target into a fully runnable workflow script -> Haiku 5.5 scans all files concurrently at 340 tokens/sec to spot candidates -> Sonnet 5.5 applies each patch and validates findings within an isolated workspace -> You eliminate wasting Opus context on dozens of agent log transcripts Opus is involved at only three specific steps: -> writing the initial workflow script before execution -> analyzing verified results once the swarm wraps up -> giving final approval prior to committing any code to git Opus architects | Haiku audits | Sonnet delivers JEV engineering applies the exact same principle a level deeper: logic paths that require no deep reasoning (choosing files, picking tools, handling retries/stops) pass through JEV in milliseconds, leaving heavy models to focus only on complex branches The complete architecture: Opus 5.5 orchestrates the core session and generates workflow.js pipeline() fans out instances of Haiku 5.5 to inspect every file parallel() schema validators eliminate false alarms directly in V8 Sonnet 5.5 applies fixes within dedicated, isolated worktrees verify double-checks all code diffs prior to summary generation Opus 5.5 processes exclusively the results that survived validation JEV routes lightweight micro-decisions in milliseconds Feed this architecture and prompt directly into Claude Code Reconfigure my Claude Code setup following this tree: 1. Execute the primary session using Opus 5.5 with ultracode enabled 2. Assign read-only scanning phases to Haiku 5.5 across all workflows, while routing code modification steps to Sonnet 5.5, running each edit inside its own isolated copy 3. Update CLAUDE.md with a new rule: assign a separate verifier agent to every issue before reporting, and terminate fix loops after two iterations without progress 4. Route fast, deterministic branching (tool selection, path routing, retry logic) via JEV Present every modification as a diff upfront do not execute changes until approved Bookmark this to stay one step aheadshow more

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of... the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long sessionshow more

I used Opus 5.5 to make a motion design... video about Haiku This is 100% motion graphics and code Short story about Opus delegating small tasks to Haiku Prompt in the commentsshow more

an Anthropic engineer just showed a cleaner way to... run Sonnet 5.5 + Opus 5.5 without wasting turns the expensive mistake is letting the wrong model stay in the loop too long. so I turned the routing logic into a prompt: → clear, scoped work stays on Sonnet 5.5 → failed checks trigger escalation → Opus gets a clean handoff, not the full transcript → cache stays warm whenever possible the numbers get weird fast: → 20K context: Opus is 1.88x per turn → 150K: 1.49x → 400K: 1.26x a late 300K switch costs $1.50 just to rebuild cache. the same handoff at 20K costs $0.10. the point is not to use Opus more. it is to make Claude prove when Opus is actually needed ↓ ↳show more

THIS IS A PURE F*CKING GOLDMINE the best REA... trick almost nobody runs yet. The idea: REA takes the app apart, Jev keeps only what's proven, and a fresh Opus 5.5 rebuilds the feature from that alone. Nothing gets copied and no guess makes it into the code, because the builder never sees the original, only the spec Jev signed off on. You just connect REA like this: npx rea-agents setup here's the split: → REA reads the feature down to the binary and writes every rule into SPEC.md → Jev checks each rule against REA's evidence and sends back anything unproven → a fresh Opus 5.5 session gets only SPEC.md and rebuilds the feature → Haiku 5.5 runs the tests against 3 intentionally broken versions Opus only shows up at three moments: → rebuilding from the approved spec → the checks Jev marks as unclear → signing off before anything ships REA reads. Jev judges. Opus rebuilds. That's the clean-room rule in one line: the model that saw the original never writes the code, and the model that writes the code never sees the original. the full tree > REA reads the app and writes SPEC.md with evidence for every rule > Jev approves or returns each rule > Opus 5.5 rebuilds from the approved SPEC.md in a fresh session > Haiku 5.5 runs the tests and the 3 broken versions > Jev routes unclear checks back to Opus > /goal keeps going until all 3 broken versions fail paste the tree and this prompt into Claude Code ↓ "Set up a clean-room rebuild around this tree: 1. Use REA to investigate [FEATURE] in [APP]. Write every behavior and rule into SPEC.md, each with the evidence REA found. 2. Send each rule to Jev. Any rule without evidence goes back to REA. 3. Start a fresh session with only SPEC.md. Rebuild the feature on Opus 5.5 without opening the original. 4. Write tests on Haiku 5.5 plus 3 intentionally broken versions. Use /goal until the rebuild passes and all 3 broken versions fail. Show me SPEC.md first. Nothing gets built until I say go." ↳ save it, it'll come in handy.show more

Jev + Opus 5.5 is the most underrated setup... in AI right now, and i don't get why nobody's talking about it. I stopped letting Opus make every small decision in my agents. Jev makes them now. My Opus bill dropped ~500% on the same tasks, same results. Here's what Jev handles: - which files and notes to load before Opus sees anything - which effort level each task actually needs - what to do when a tool fails - which tests to run, and when to stop Opus only gets called for the hard reasoning. Every decision is a typed result the host checks before it runs. The exact prompt to set this up in your workflow is below.show more

New Claude Sonnet 5 performs at GPT 5.5 level... 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other modelshow more

Claude Code tip: if Opus 5.5 is already your... main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."show more

Remember the jelly watermelon slice? Now there’s a whole... watermelon 🍉 Using Claude Opus 5.5, I made a full jelly watermelon you can cut into pieces with a knife right in your browser First, squish and stretch the whole thing, then grab the knife and slice it however you like. The pieces stay jiggly too - you can grab and squish them individually This one cost $30.07. My jelly experiments seem to be getting more expensive If Opus 5.5 can already do this, imagine what Claude Fable 5.5 will be able to create 👀show more

Anthropic shouldn't have revealed this plugin. Its name speaks... for itself "You should know" Its capability: Opus 5.5 writes, the second agent reads, garbage aside: you get only important and reliable information Opus 5.5 can run continuously for 60 minutes, generating long summaries that nobody checks And this is what many miss: > a test it skipped "for now" > a file it modified even though you didn't ask for it > a warning "this might break the system" hidden somewhere at the bottom All of this is written there. You just never saw it Now another AI checks the text for you This is an automatic feature Enabled with a single line: ⁠/plugin enable cc-plugin-you-should-know@builtin⁠ Do this when you start working: > Open Claude Code > Paste the line above > Give Opus a long task and see how it analyzes the text and eliminates obvious errors Now the agent won't waste your money: you will get the expected result Bookmark thisshow more

This is f*cking insane. This tip saved me thousands... of dollars. run Opus 5.5, Sonnet 5.5, and Fable 5.1 together, and stop burning Opus on work it was never needed for. the whole idea in one line: the strong model plans, the mid-tier model executes, Fable stays quiet until it's actually needed. roles, broken down: Opus 5.5, high effort, owns the plan and ships the final code Sonnet 5.5, medium effort, splits into explorer (reads the codebase), worker (edits files, runs tests), researcher (pulls docs) Fable 5.1, called through /advisor fable, reads everything happening in the session but stays silent unless something's actually wrong three moments where Fable speaks: → a plan goes out: is this actually the right call? → the same failure shows up again: is the search going nowhere? → the task gets marked finished: did something get skipped? Jev engineering does the same thing one level down. the forks that don't need real thought, which file, which tool, keep going or stop, go straight to Jev and come back in under half a second. the big models only ever see the forks that genuinely need a decision. anyone still running one model for everything is paying Opus prices to decide whether a file exists. drop this into Claude Code: "Rebuild my Claude Code setup around this structure: Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: sonnet, effort: medium on each. If an existing subagent is locked to a different model, leave it as is and just list it. In ~/.claude/settings.json, set effortLevel to high and advisorModel to fable. Check for anything disabling the advisor, CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches, plus CLAUDE_CODE_EFFORT_LEVEL, which can override subagent effort settings. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: check in with the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."show more

ex-lead Anthropic engineer leaked a chip that runs any... company 24/7 and it’s f**king unreal REA → OPUS 5.5 → SONNET 5.5 → FABLE 5.1 all combined into one system this is REA as a chip: 5 layers, 5 dies, 1 system. REA core in the middle, 4 Claude models around it one model plans, one does the work, one makes the hard calls, and REA reverse-engineers any business you point it at only one exists in the world, valued at $100,000+ save it, this is a whole company in the palm of your hand ↓show more

Jelly King: Opus 5.5 Mogged Astra, Fable and Sonnet... In my jelly tests, Opus is in a league of its own right now. And it’s not just the wobble - the materials and detail are on another level too Look at this citrus slice. Glossy flesh, visible segments, soft folds when you pull it. Astra bends too, but those sharp creases look more like a crumpled wrapper than jelly Opus wins this one for me, and it’s cheaper. Maybe only Fable 5.5 can take the crown from Opus 👑 Estimated API cost: Opus 5.5 - $7.57 ChatGPT-6 Astra - $10.15 Would you still pay more for Astra after watching this? 👀show more

$35 OF FREE CLAUDE OPUS 5 CREDITS FOR A... WEEK, NO CARD ANYWHERE • the credit > Sign up with Google and the trial activates on its own, nothing to claim manually: > Opus 5 sits alongside Opus 4.8, Sonnet 4.6 and Haiku on the same key. > The window runs a week from activation. • wiring it up > base url: > model id: claude-opus-5 > In OpenCode Desktop hit Ctrl+, and add a custom provider with the id aerolink. > The same key drops into Codex, Cursor and Claude Code with nothing else changed. One key, not locked to one client -> every tool that takes a custom OpenAI-compatible endpoint reads it the same way. It routes through a third-party proxy rather than an official Anthropic channel, so keep client work off it ↓show more

Opus 5.5 quite literally k*lled GPT-6 Astra. I asked... Opus 5.5 to build a world in Unreal Engine and fill it with AI agents (Opus, Astra, Sol, Grok). Higgsfield built the assets in Blender. I left my laptop open overnight. The build took over 20 hours. The agents had one instruction: build a working society, allocate roles to each other, and evolve. Then I woke up on them beating the sh*t out of each other. Seems the frontier paced itself. Last minutes of failed society captured below:show more

Lauren from the Grok Bot team just confirmed it:... every bot now runs on Claude Opus 5.5 and each one can spin up its own cloud agents running Cursor’s models this is f*cking insane... so i built the harness on top of it, in one prompt: Opus 5.5 leads and builds, Grok scouts live X and the web, every claim needs two sources, a red team attacks the draft before you see it, and every run gets logged so the next one starts smarter you stop prompting models. you sign off on results. paste it into Grok Bot or Claude and thank me later all 10 steps, the workflow, and real examples below ↓show more

I built a website that plays endless lofi over... pixel-art cities at night using Opus 5.5 The music isn't a playlist. A brand-new track is composed in your browser every few minutes. Put it on while you work:show more

Claude Opus 5.5 designed the PCB for Kookabus-01. Then... I asked it for a 3D printable enclosure. First print. Board drops straight in and every connector lines up with its cutout! Same model did the board and the box. Claude is really impressing me.show more

we compared Gemini 3.1 Pro, Opus 4.7, and GPT... 5.5 to Kimi K2.6, Xiaomi Mimo v2.5, and Qwen 3.6 Max in average, closed source are faster. GPT 5.5 and Opus 4.7 the fastest. Kimi K2.6 comes after. It keeps up thanks to its native INT4 quantization. MiMo took the longest, but the refinement and aesthetic only ranks after Gemini 3.1. as if a mini Gemini. Its slow cuz it's trained for long-horizon agentic work. Claude Opus 4.7 is blooming in a very different style, probably because Anthropic trains for taste, not just accuracy.show more