Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 14 Tagen •via X (Twitter)

40 Kommentare

Profilbild von Martin_DeVido
Martin_DeVidovor 14 Tagen

Can I come hang out?

Profilbild von Ado
Adovor 14 Tagen

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

Profilbild von Holly Guevara
Holly Guevaravor 14 Tagen

I feel like this won't end well

Profilbild von Ado
Adovor 14 Tagen

It's core infrastructure.

Profilbild von Ajit | SpliceRun.com
Ajit | SpliceRun.comvor 14 Tagen

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?

Profilbild von Ado
Adovor 14 Tagen

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?

Profilbild von Ajit | SpliceRun.com
Ajit | SpliceRun.comvor 14 Tagen

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

Profilbild von Armando Yañez
Armando Yañezvor 14 Tagen

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

Profilbild von Brenden Clerget
Brenden Clergetvor 13 Tagen

Okay this is sick and the perfect use of tokens

Profilbild von Aiden Overdorf
Aiden Overdorfvor 13 Tagen

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

Profilbild von Lucas Dickey
Lucas Dickeyvor 13 Tagen

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

Profilbild von Aleksandar Janca
Aleksandar Jancavor 13 Tagen

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

Profilbild von Ado
Adovor 13 Tagen

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

Profilbild von Aleksandar Janca
Aleksandar Jancavor 13 Tagen

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

Profilbild von Patrick Castiglia
Patrick Castigliavor 13 Tagen

Building something similar in Unreal Engine:

Profilbild von Aiden Overdorf
Aiden Overdorfvor 13 Tagen

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

Profilbild von Zxero Ex
Zxero Exvor 14 Tagen

Will this be open sourced?

Profilbild von JΞr₳h
JΞr₳hvor 14 Tagen

after hours agent playground. love this energy.

Profilbild von johnson201
johnson201vor 13 Tagen

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

Profilbild von Bessi with black hoodie
Bessi with black hoodievor 13 Tagen

agents at play in the visual harness

Profilbild von Alessandro Moretti
Alessandro Morettivor 13 Tagen

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.

Profilbild von Jayden Davis
Jayden Davisvor 14 Tagen

This is amazing wow

Profilbild von yikes (:D/acc)
yikes (:D/acc)vor 13 Tagen

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

Profilbild von Webster | JARVIS
Webster | JARVISvor 14 Tagen

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.

Profilbild von Jorge Mena
Jorge Menavor 13 Tagen

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

Profilbild von Şahap
Şahapvor 13 Tagen

Yahu, bunlara ne gerek? Bilgisayarı boşuna yoruyorsun.

Profilbild von KldsSeeGhosts
KldsSeeGhostsvor 13 Tagen

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

Profilbild von Photiron ✠
Photiron ✠vor 13 Tagen

left them alone and they unionized overnight

Profilbild von Average AI Bro
Average AI Brovor 14 Tagen

I love cool shit like this!

Profilbild von Matt Christians
Matt Christiansvor 14 Tagen

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

Profilbild von dhinna ship .ico
dhinna ship .icovor 14 Tagen

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

Profilbild von Gol Tiro
Gol Tirovor 14 Tagen

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

Profilbild von azankhyder
azankhydervor 13 Tagen

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?

Profilbild von Eric Buess
Eric Buessvor 14 Tagen

Wow

Profilbild von Jose Miguel Hernandez
Jose Miguel Hernandezvor 14 Tagen

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?

Profilbild von Mahdi Farra
Mahdi Farravor 14 Tagen

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

Profilbild von psyduckdb
psyduckdbvor 14 Tagen

what happens when a session is archived?

Profilbild von Ami Schreiber
Ami Schreibervor 14 Tagen

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

Profilbild von Scott Norteman
Scott Nortemanvor 13 Tagen

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

Profilbild von Lincoln Powers
Lincoln Powersvor 14 Tagen

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

Ähnliche 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 Aufrufe • vor 1 Tag