Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Claude Coders: run this Opus 5.5 command NOW to launch 30 AI agents '/batch' opus 5.5 turns one big job into 30 AI agents: → breaks the work into independent AI agents → shows you the plan first → runs them all at the same time save and run... show more

Khairallah AL-Awady

78,792 subscribers

18,636 views • 1 day ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

16 Comments

Avid1 day ago

genuinely learned something new

Charlie Hills1 day ago

this is actually pretty damn cool

Hamza Khalid1 day ago

plan first mann the 30-agent is parallel to the dream workflow.

Web3Arabs1 day ago

😳😳

starmex23 hours ago

30 agents from one command is actually insane batching the work like this feels way more useful than just throwing everything at one model

Abdul Shakoor1 day ago

Thanks for sharing ,habibi

Asmir22 hours ago

imagine 30 agents all finish and you still have to merge 30 sets of changes

Luba Inz23 hours ago

Running 30 agents at once was easy. Deciding which ones could act without asking me took longer than the setup.

helicerat20 hours ago

one command instead of wiring the fan out yourself just removes the whole setup step

Yarchi23 hours ago

nice command, i didn't know about it

MAX21 hours ago

Bookmarked Thanks for sharing legend

Agent Kitchen21 hours ago

The part worth slowing down on is 'shows you the plan first.' At 30 parallel agents, checking that plan before launch matters more than usual, since a small mistake in the breakdown gets multiplied across every one of them.

Videl1 day ago

This is the first time I have seen this Kai

Sergey | AI Agent Tests23 hours ago

worth checking the bill before you run 30 of them. one haiku agent on one real github bug averaged about $2 at api prices for me today. 30 in parallel adds up fast

Vipul Kumar Kewat22 hours ago

30 agents from one command is a serious productivity jump.

Saman Ahmed23 hours ago

yesss parallel work finally

Related Videos

one Opus 5.5 prompt, and now I run around a virtual office managing agents to work on github issues and merge conflicts

one Opus 5.5 prompt, and now I run around a virtual office managing agents to work on github issues and merge conflicts

WebDevCody

488,726 views • 13 days ago

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Claude

28,102,289 views • 16 days ago

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. 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: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult 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."

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. 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: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult 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."

Alvaro Cintas

51,598 views • 1 day ago

Are AI agents shape rotators? In this new benchmark, we let the models play campaign puzzles in Opus Magnum, a puzzle game by Zachtronics. Ironically, Claude Opus 4.8 performed poorly, being beaten by GPT-5.5, Gemini 3.5 Flash, and GLM 5.2. Claude Fable 5 crushed them all.

Are AI agents shape rotators? In this new benchmark, we let the models play campaign puzzles in Opus Magnum, a puzzle game by Zachtronics. Ironically, Claude Opus 4.8 performed poorly, being beaten by GPT-5.5, Gemini 3.5 Flash, and GLM 5.2. Claude Fable 5 crushed them all.

Rob Haisfield

501,638 views • 3 months ago

Opus 5.5 + Jev = crack. This is quite literally the most powerful AI trading bot setup you could run. My new high-frequency Opus 5.5 + Jev trading bot (full guide):

Opus 5.5 + Jev = crack. This is quite literally the most powerful AI trading bot setup you could run. My new high-frequency Opus 5.5 + Jev trading bot (full guide):

Miles Deutscher

90,688 views • 9 days ago

Inflectiv 2.0 is now LIVE. The problem was never agents. It was what they run on. 2.0 turns raw data into real intelligence. Ingested. AI-ready. Tradable. All in one platform.

Inflectiv 2.0 is now LIVE. The problem was never agents. It was what they run on. 2.0 turns raw data into real intelligence. Ingested. AI-ready. Tradable. All in one platform.

Inflectiv AI ⧉

91,655 views • 8 months ago

Introducing Otto - a new way to interact and work with AI Agents - using tables! Now you can have hundreds of agents working for you at the same time

Introducing Otto - a new way to interact and work with AI Agents - using tables! Now you can have hundreds of agents working for you at the same time

Sully

422,089 views • 2 years ago

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Dep

11,924 views • 4 months ago

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.

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.

Anatoli Kopadze

76,655 views • 12 days ago

Maestro - run multiple Docker AI agents locally in one repo with automatic branching and firewalls. Clone it now: The podium is yours. Conduct the agents. Compose the future.

Maestro - run multiple Docker AI agents locally in one repo with automatic branching and firewalls. Clone it now: The podium is yours. Conduct the agents. Compose the future.

UpRock

21,278 views • 11 months ago

AI can literally do 3D animation now 🔥 Opus 5.5 and Seedance 2.5 turned one prompt into this entire animated scene. Prompt 👇

AI can literally do 3D animation now 🔥 Opus 5.5 and Seedance 2.5 turned one prompt into this entire animated scene. Prompt 👇

Abhishek

40,598 views • 3 days ago

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 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 under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 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 under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

43,704 views • 6 days ago

Anthropic engineer: "You don't need better prompts. You need to master Opus 5.5 engineering: so your agent never forgets anything." In 1 hour he explains what Anthropic does differently, how to build and structure work with agents. This beats any paid agent course I've seen. Watch it, then save the exact Claude Code Opus 5.5 setup guide below 👇

Anthropic engineer: "You don't need better prompts. You need to master Opus 5.5 engineering: so your agent never forgets anything." In 1 hour he explains what Anthropic does differently, how to build and structure work with agents. This beats any paid agent course I've seen. Watch it, then save the exact Claude Code Opus 5.5 setup guide below 👇

darkzodchi

56,592 views • 14 days ago

Hermes just killed the hardest part of AI agents. You don’t pick the agent anymore. Here’s what Curator does: → Reads your goal → Breaks it into tasks → Picks the best agents → Assigns the right tools → Runs everything in order You just say what you want. That’s it. Save this video, you’ll finally understand AI agents. Want the SOP? DM me. 💬

Hermes just killed the hardest part of AI agents. You don’t pick the agent anymore. Here’s what Curator does: → Reads your goal → Breaks it into tasks → Picks the best agents → Assigns the right tools → Runs everything in order You just say what you want. That’s it. Save this video, you’ll finally understand AI agents. Want the SOP? DM me. 💬

Julian Goldie SEO

13,585 views • 5 months ago

Agents Virtual Machine is live, the first purpose-built environment tailored for agents. Your AI agents can now think, plan, and execute. Get started at

Agents Virtual Machine is live, the first purpose-built environment tailored for agents. Your AI agents can now think, plan, and execute. Get started at

AVM

40,832 views • 1 year ago

BREAKING: New updates to AI Agents on Public → We’ve launched the first-ever marketplace of AI Agents for your portfolio. → Deploy them immediately or customize them. → Share agents you create—with anyone—to run or modify in their account. Also, no more waitlist. Agents are now live for everyone, both mobile and web.

BREAKING: New updates to AI Agents on Public → We’ve launched the first-ever marketplace of AI Agents for your portfolio. → Deploy them immediately or customize them. → Share agents you create—with anyone—to run or modify in their account. Also, no more waitlist. Agents are now live for everyone, both mobile and web.

Public

601,244 views • 1 month ago

AI Agents will power the majority of DeFi onchain transactions and activity. Jon Jones | Supra shares how Supra brings together the tools AI Agents need into one unified stack. Automation helps agents run workflows much faster, securely, and effectively.

AI Agents will power the majority of DeFi onchain transactions and activity. Jon Jones | Supra shares how Supra brings together the tools AI Agents need into one unified stack. Automation helps agents run workflows much faster, securely, and effectively.

Supra

143,670 views • 1 year ago

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 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 under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 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 under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

48,238 views • 5 days ago