Pinned Tweet
I built /cockpit for Claude Code. It's a sidebar that shows what the main thread and every subagent are doing, live
Once Claude launches a few agents in the background, the chat tells me they started and then I am stuck waiting and I wanted something different, I wanted to see which one is still working and on what, which one has gone quiet, which one is stuck until I approve a command and what the batch has cost me so far
So every agent gets a block with its elapsed time, tool calls, errors, context size, estimated cost, model, and the tool call it's on this second. An agent with no activity for 3 minutes turns yellow, and one waiting on approval turns red. Click an agent to read its transcript, stop it, or send it a note
The main thread has its own block with a context bar and a countdown on the prompt cache. Background shells, monitors and workflows are listed too, and I get a notification when the batch finishes, so I can go work on something else
github.com/MPMyburgh/claude-…
Gemini Neon is absolutely nuts, Google are back baby, 3 rapid fire releases and all of them have been bangers, if this doesn’t scream RSI I don’t know what does, so glad we’re back at the stage where all the frontier labs are fighting for the podium again!
36
New quirk I have found with Fable 5.2 is that it is constantly using the same builder agent even when it’s pushing 500k on context, he is even aware of it, then with agent cache being only about 5 minutes in any long running tasks it hammers your usage 🫠
Long agentic task so a lot of this happened in sleeping hours but good to keep note of
1
110
Just to be clear, when you put rules in your global AGENTS.md or CLAUDE.md or even repo level, you need to know that these can and will be ignored, by making use of permissions/hooks etc you need to block and redirect agents mechanically, putting "do not delete my home drive" doesn't mean anything
3
31
Very very interesting that all the devfluencers are hating on OpenAI, and then the general public is quite happy with the performance, and Anthropic IPO literally around the corner #conspiracy
1
28
Interesting, I got hit with a cybersecurity flag for doing defensive work on my own work with Mythos 5.2, even while part of the Cyber Verification Program (CVP)
The revised prompt worked quite well though. Once it confirmed I own the project, it was comfortable continuing the red team exercise
49
On the same machine and the same model, a fresh Claude Code session starts at 20.9k tokens in the CLI and 49.3k in the GUI.
Most of the gap is the MCP. The GUI loads 16.6k of tool definitions upfront, while the CLI tools loads its tools on demand and starts at 0, and the GUI's system prompt is 11.1k against the 3.5k
For one session that's fine, since 49.3k is 5% of a 1M Window, but I lean very heavily on subagents, and each one starts its own context and pays that overhead again, so your usage takes a massive hit
I am very much still married to the CLI, the GUI has some really nice QOL features but that's about it
4
2
57
It’s concerning that everyone is critiquing Qwen4-max for only somewhat improving over Qwen3.8-max and blaming it on Western labs blocking distillation.
Even if that’s the case, the slowdown and death of open source LLMs should concern us more.
A monopoly would look a lot different from what we have now with Anthropic and OpenAI: non-existent limits and crazy pricing. The Chinese models put a lot of pressure on the pricing and service of the Western labs. DeepSeek Flash v4.1 led to price cuts across all the major labs.
Just keep it in mind!
21
Just got uncalled for access to a new flash model…
Had to divert my eyes and call the police, wouldn’t recommend
1
32
My usage reset is on a Sunday evening, I make an active effort to burn through 100% by Friday, AI makes it too easy to feel productive and for dopamine starved brains it’s addictive, at least it allows me to switch off over weekends, anyone else?
1
23
Insane that we’re living in our version of the dot com boom and a lot of people are complaining about usage limits instead of watching AI go brrr
15
You should be using other models than Opus and Fable as well, smarter models make people lazier, when subsidisation ends, you’ll end up struggling to keep up because the skills for proper plans and implementation guidelines have atrophied
1
31
Oh my word, finally! @TheWholeDaisy you did it!
You can now build custom themes for Claude Code on desktop with mods! Change the colors, add an animated background, and make it your own.
Just tell Claude how you want it to look, or get started quickly with the theme-examples plugin. We'd love to see what you make!
1
35
Michael Myburgh retweeted
I built /cockpit for Claude Code. It's a sidebar that shows what the main thread and every subagent are doing, live
Once Claude launches a few agents in the background, the chat tells me they started and then I am stuck waiting and I wanted something different, I wanted to see which one is still working and on what, which one has gone quiet, which one is stuck until I approve a command and what the batch has cost me so far
So every agent gets a block with its elapsed time, tool calls, errors, context size, estimated cost, model, and the tool call it's on this second. An agent with no activity for 3 minutes turns yellow, and one waiting on approval turns red. Click an agent to read its transcript, stop it, or send it a note
The main thread has its own block with a context bar and a countdown on the prompt cache. Background shells, monitors and workflows are listed too, and I get a notification when the batch finishes, so I can go work on something else
github.com/MPMyburgh/claude-…
Michael Myburgh retweeted
BREAKING: Nvidia, $NVDA, CEO Jensen Huang has resigned as CEO, President, and member of the Board of Directors, effective immediately.







