Claude Code Just Dropped /Goal. (Master it in 8 Minutes)
An 8-minute blueprint for the new /goal command — two agents, one finish line, zero babysitting.
May 17thA 5-minute explainer that breaks UltraCode into its two parts, demos 48 agents in parallel, then reveals the cost.
UltraCode is not a smarter model but a project manager that forks your task across up to 100 simultaneous agents, each verified by a separate review agent before results return to you.
UltraCode bundles two distinct capabilities: xhigh thinking (one step below max effort per message) and dynamic workflows (Claude plans the task, forks it across up to 100 agents simultaneously, and routes output through a verification agent). The key distinction from Max is that Max is purely a thinking depth setting while UltraCode adds the parallel team on top of near-max thinking. The trade-off is direct: better output on complex parallel tasks, dramatically higher token cost.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →
One-worker vs. 100-worker analogy; cost tease planted; three-part agenda card shown.

Shows the /effort slider from low to ultracode; explains UltraCode sits beside Max, not above it.

xhigh thinking defined as one step below max per message; dynamic workflows defined as parallel agent team with built-in verification.

One click from the /effort menu activates it session-wide; no per-task invocation needed.

Max is a pure thinking-depth setting; UltraCode adds the agent team on top of near-max thinking. Distinct tools, not interchangeable.

Food truck business research prompt; 48 agents visible in the lightning bolt counter; output is a complete multi-section PDF starter guide.

UltraCode is the most expensive Claude Code mode by a large margin -- officially acknowledged in the docs. Bar chart drives the point home.

Two-sentence recap of both UltraCode components; subscribe ask; link to prior video.
UltraCode is not a step up from Max -- it is a different product: a parallel agent team with built-in QA, and the cost scales accordingly.
“UltraCode is just two things that are bundled together.”
“It's actually not an effort at all.”
“UltraCode is the most expensive way to run Claude Code by a lot.”
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
What if instead of one worker grinding through a task for an hour, you could hand it to a hundred workers who each take a piece and run simultaneously? That is the premise the video opens with -- and it turns out to be a literal description of how UltraCode operates, not just a metaphor.
The three-layer architecture that defines how UltraCode differs from all other effort levels.
The /effort menu hierarchy, with ultracode sitting outside the linear thinking-depth progression.
“If this was helpful, do me a favor. Please subscribe.”
Standard mid-video ask at ~2:50 before the demo, plus a closing subscribe + related-video pair. The mid-video timing slightly undercuts demo momentum.
00:00
00:05
00:09
00:12
00:17
00:21
00:23
00:27
00:31
00:34
00:37
00:42
00:45
00:49
00:53
00:56
00:59
01:03
01:07
01:11
01:15
01:19
01:22
01:26
01:30
01:33
01:37
01:41
01:45
01:48
01:52
01:55
01:59
02:03
02:08
02:10
02:15
02:17
02:20
02:25
02:28
02:31
02:36
02:39
02:43
02:45
02:50
02:55
02:57
03:03
03:05
03:09
03:14
03:16
03:20
03:25
03:26
03:30
03:34
03:38
03:41
03:46
03:48
03:53
03:58
04:00
04:04
04:09
04:11
04:15
04:19
04:23
04:27
04:30
04:34
04:37
04:41
04:44
04:48
04:52An 8-minute blueprint for the new /goal command — two agents, one finish line, zero babysitting.
May 17thBoris Cherny, the creator of Claude Code, walks through a live Cowork demo and unpacks the 13-tip viral setup thread that got 99K bookmarks.
January 23rdA 48-minute walkthrough that takes you from blank screen to a fully automated AI assistant — seven steps, no code required.
April 10thA 19-minute live build showing how to make Claude Code skills that grade their own output, remember past sessions, and get better every time you run them.
June 3rdA 14-minute operating manual for turning Claude Code from a chat toy into a compounding personal AI infrastructure.
May 27thA 13-minute sprint through 27 production habits distilled from 500+ hours inside Claude Code.
March 29th