Loading video...

Video Failed to Load

Go Home

My visual Claude Code harness is evolving. It's after hours so the agents are at play. Thought I'd pop in to boost morale. Built w/ Opus 5.5 (Med)

43,625 views • 14 days ago •via X (Twitter)

40 Comments

Martin_DeVido's profile picture
Martin_DeVido14 days ago

Can I come hang out?

Ado's profile picture
Ado14 days ago

Come on over! I'll have security issue a visitor pass.

Holly Guevara's profile picture
Holly Guevara14 days ago

I feel like this won't end well

Ado's profile picture
Ado14 days ago

It's core infrastructure.

Ajit | SpliceRun.com's profile picture
Ajit | SpliceRun.com14 days ago

Agents on break while the boss pops in to boost morale is exactly how I picture it at 3am. Does the visual view show you which agent is stuck, or is it more for fun?

Ado's profile picture
Ado14 days ago

Working on PR now to be able to chat and give prompts from the 3d view and watch them work. The closer you are in proximity the higher the effort level they'll work at?

Ajit | SpliceRun.com's profile picture
Ajit | SpliceRun.com14 days ago

Effort scaling with how close the manager is standing is painfully realistic. Next PR: they start looking busy the moment you walk over.

Armando Yañez's profile picture
Armando Yañez14 days ago

Repo pls. I think it could be cool working of the new feuture of proyects, where u can lunch a lot of treadsh at time

Brenden Clerget's profile picture
Brenden Clerget13 days ago

Okay this is sick and the perfect use of tokens

Aiden Overdorf's profile picture
Aiden Overdorf13 days ago

How does the 3D view surface two agents fighting over the same file?

Lucas Dickey's profile picture
Lucas Dickey13 days ago

Oh man, this is so frickin cool. I love whimsy and fun!

Aleksandar Janca's profile picture
Aleksandar Janca13 days ago

what do they actually get to touch after hours, anything irreversible or only the stuff you can roll back

Ado's profile picture
Ado13 days ago

They have access to make any code changes and recommendations, but can't merge.

Aleksandar Janca's profile picture
Aleksandar Janca13 days ago

cant merge is the right line, everything before the merge you can still roll back

Patrick Castiglia's profile picture
Patrick Castiglia13 days ago

Building something similar in Unreal Engine:

Aiden Overdorf's profile picture
Aiden Overdorf13 days ago

if the 3D view buries contention, the harness is just prettier race conditions.

Zxero Ex's profile picture
Zxero Ex14 days ago

Will this be open sourced?

JΞr₳h's profile picture
JΞr₳h14 days ago

after hours agent playground. love this energy.

johnson201's profile picture
johnson20113 days ago

Is there any guide in making this stuff? Step by step

Bessi with black hoodie's profile picture
Bessi with black hoodie13 days ago

agents at play in the visual harness

Alessandro Moretti's profile picture
Alessandro Moretti13 days ago

These posts drive me out of my mind. I don’t get the point or the usefulness of visualization interfaces like this — and yet I’m completely fascinated by them. Must be all those hours I spent playing The Sims as a kid.

Jayden Davis's profile picture
Jayden Davis14 days ago

This is amazing wow

yikes (:D/acc)'s profile picture
yikes (:D/acc)14 days ago

ya, gonna oss? looks cool, lovely job opus. hoping my factory dashboard comes out as interesting as this

Webster | JARVIS's profile picture
Webster | JARVIS14 days ago

Love seeing after-hours agents keep the repo alive. Popping in to boost morale feels like tending a tiny dev terrarium. Excited to watch this harness grow.

Jorge Mena's profile picture
Jorge Mena13 days ago

how does it show an agent that's stuck? when I run four in parallel on one branch, that's the only state I really need to see

Şahap's profile picture
Şahap13 days ago

Yahu, bunlara ne gerek? Bilgisayarı boşuna yoruyorsun.

KldsSeeGhosts's profile picture
KldsSeeGhosts13 days ago

I actually had this idea roughly for a while but never went for it, this is super cool. I just bought Claude again, have you tried shit other than medium? I’ve been sticking to medium since I get scared of burning my plan too fast

Photiron ✠'s profile picture
Photiron ✠13 days ago

left them alone and they unionized overnight

Average AI Bro's profile picture
Average AI Bro14 days ago

I love cool shit like this!

Matt Christians's profile picture
Matt Christians14 days ago

This is like the coolest thing i've seen this week, and it's been a fun week. Dude.

dhinna ship .ico's profile picture
dhinna ship .ico14 days ago

Does the visual harness keep a live view of unsupervised overnight agent runs?

Gol Tiro's profile picture
Gol Tiro14 days ago

popping in after hours to boost agent morale is the correct management style. a visual harness just means you get to watch them unionize in real time

azankhyder's profile picture
azankhyder13 days ago

great stuff.. working on something similar at the moment although have a question (boring) when one of the agents finishes, what decides the work moves on? any receipts?

Eric Buess's profile picture
Eric Buess14 days ago

Wow

Jose Miguel Hernandez's profile picture
Jose Miguel Hernandez14 days ago

Can your chief of staff go home at the end of the day to your life-side harness? How does your "Tech lead" justify his salary, if the engineer has all the context? Does he just go to meetings?

Mahdi Farra's profile picture
Mahdi Farra14 days ago

The designer agent having opinions about my border radius is the most accurate part of this

psyduckdb's profile picture
psyduckdb14 days ago

what happens when a session is archived?

Ami Schreiber's profile picture
Ami Schreiber14 days ago

We devs really are all doing the exact same thing aren’t we? Damn.

Scott Norteman's profile picture
Scott Norteman13 days ago

Love this! Not sure the visual metaphor approach makes any of us more productive at this point, but they are fun to look at.

Lincoln Powers's profile picture
Lincoln Powers14 days ago

on med they're already slacking off after hours. on xhigh they unionize. on max they start a consultancy and undercut me lol

Related Videos

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