Nuski

Claude Code's agent teams are powerful. Getting them to actually work is a nightmare. Swarm Orchestra fixes that. Without it: • 20+ runaway agents from teammates spawning teammates • Claude guesses the team structure • TeamDelete fails silently and leaves stale state With it: you describe the work, approve a plan, agents spawn and coordinate on their own. v2 just added mid-turn inter-agent messaging via a PreToolUse hook. Agents can course-correct each other without waiting for a turn boundary. github.com/NuskiBuilds/sw…

Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.

@jessmartin Made a skill/plugin to be able to reliably call them after I noticed Claude having trouble knowing how to use the right tool (TeamCreate) /swarm github.com/NuskiBuilds/sw…

Why is no one talking about Claude Code's agent teams feature? I guess it's because people aren't using agents as much as they use skills?

Been waiting a month for Anthropic to answer a simple usage question about Claude Code subscriptions Have I been ghosted

@trq212 love it other than chat history not saving even with tmux

Have you tried the new Claude Code renderer? What has your experience been like? If you haven't, you can enable it with: CLAUDE_CODE_NO_FLICKER=1 claude

I was never one to agree that Anthropic was nerfing Claude. Recently, my autistic pattern recognition can’t let this get go because it’s been a glaring issue that we’ve been gaslit about. They are 100% nerfing it. I don’t have data like, like the researcher above, to back up my claims. But the Opus 4.6 and Claude in general, we had prior to February, was incredible. This was: - Prior to the scaling. - Prior to the influx of users. - Prior to them pushing out a new feature every hour. - Prior to them not fixing anything the power users are screaming about. It WAS incredible, now it’s back to eh. - The “should I continue” is a wild one actually. It’s fucking infuriating when we finish something, that has a defined set of instructions and todos, the model tries to “stop here for the day” or “we’ve done a lot today, should we stop for the day, and commit?”. - The going in circles and self contradiction is also a crazy one. That with the fact that opus seems to be making changes, that make no sense, and when plainly asked why that change was made, the model said it didn’t read the code! Like what the fuck?! - The burning of tokens is also wild. I asked Claude to please fix a specific label, on a view. That’s it. I step away, mind you the model wasn’t on auto accept or anything, and come back to 30 mins of wasted time. Then has more questions for me after my tokens were burned for 30 minutes. - Putting the model into the plan mode, prior to making changes, also used to be a banger. The model would spawn subagents, set things up, orchestrate. None of that happens in plan mode anymore. Plan mode seems to be a complete waste of tokens and time. Especially when you plan for 30 minutes. Accept the plan. Then the model does nothing for another 30 minutes, aside from burning tokens. Unsure wtf is happening but I simply want the banger service back, from prior to February, that I am paying $200/month for. TBH, I would have paid $500/month for that version of Claude. That’s how bad the current version is. This Claude has me programming manually again. Months of incredible work with Claude. Now just slop. cc: @bcherny @trq212 @AnthropicAI

@trq212 When are Max users going to be able to have access to auto mode?

you'll need to explicitly prompt Claude Code to use it, but the Monitor Tool is super powerful e.g. "start my dev server and use the MonitorTool to observe for errors"

Anthropic CEO: “Disagreeing with the government is the most American thing in the world.”

Today I$rael tried to kill me in a targeted airstrike in southern Lebanon as I was reporting on was the targeting of bridges and the forced displacement of 1 million people, an ethnic cleansing operation on a larger scale than the Nakba I have absolutely no doubt that this was deliberate. Despite claims there were no warnings ahead of the strike and no notifications sent to the Lebanese Army who allowed us to film As we have seen in Gaza they want to silence journalists who document and report their war crimes It is the western powers who provide political and military support for I$rael, arming it to the teeth to carry out genocide in Gaza and ethnic cleansing here in Lebanon. They are not simply complicit, but active participants and should be held accountable for their actions. But if I$rael thinks today’s strike will silence us and keep us out of the field they are very, very mistaken

@trq212 @dexhorthy if anyone is curious, open to all feedback github.com/NuskiBuilds/sw…

@trq212 @dexhorthy teammates spawned via TeamCreate can actually invoke skills unlike pure subagents Swarm Orchestra uses this Orchestrator just says 'Use /teammate' in the handoff and the teammate loads it itself no duplicate instructions needed

soooo subagent skills…feels like subagent instructions will overlap with skill and ppl won’t know what to put where. I can only assume that this will eventually replace custom subagents This also explains why they recently made it so subagents can’t invoke skills. I still think We need a solution for instruction modules orthogonal from context forking - let me use a skill in either parent or subagent dynamically based on a prompt @trq212 !! Eg “use the playwright skill for X” or “launch a subagent to use the playwright skill for X” or even “use a play write subagent for X” Today I STILL have to maintain two copies of the instructions to be able to run in parent or subagent!

Imagine monitoring the situation from here

hey @amorriscode @bcherny @trq212 built this to handle reliable spawning, cleanup, and inter-agent messaging for Claude Code agent teams would love feedback from you all!

Claude Code's agent teams are powerful. Getting them to actually work is a nightmare. Swarm Orchestra fixes that. Without it: • 20+ runaway agents from teammates spawning teammates • Claude guesses the team structure • TeamDelete fails silently and leaves stale state With it: you describe the work, approve a plan, agents spawn and coordinate on their own. v2 just added mid-turn inter-agent messaging via a PreToolUse hook. Agents can course-correct each other without waiting for a turn boundary. github.com/NuskiBuilds/sw…

@trq212 I have noticed a huge improvement tbh, massive upgrade

i think we might have undersold 1M context tbh, the performance is so so good, I really just don't clear the context window much these days

@amorriscode @bcherny @trq212

A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.

A few end of week ships: You can now set effort to 'max' which reasons for longer and uses as many tokens as needed. This will spend your usage limits more quickly so you have to activate it per session. Hit /effort to try it.

1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.