Coy Geek

Hey, This is a fantastic feature request, and something I've run into myself. It's a great point that specialized tools, especially verbose ones managed via MCP, can really clutter up...

The most direct way to see the thinking and tool calls from subagents is to start Claude Code with the `--verbose` flag. ```bash claude --verbose ``` The CLI reference documentation...

That's a great question @igamenovoer Based on my reading of the documentation, it seems **subagents do not inherit the "ultrathink" instruction** from the main agent. Here's why: The documentation on...

There's Open Telemetry. Otherwise, put down what you want to see in a new GitHub issue as a feature request.

Based on the provided documentation bundle, here is an analysis of the status of the features mentioned in the GitHub issue. ### Summary The documentation team has made significant progress,...

Based on the latest documentation bundle and the changelog, here is the follow-up status report. ### Status Update: CLI Reference Updated The documentation team has addressed the biggest gap from...

I proposed a potential high-level architectural plan on how to achieve this in my github issue #4897

Hey, that's a great suggestion. I was looking into the same thing for a project where I need to be really specific about what external resources the agent can access....

Hey there, This is a great suggestion. It would be a huge quality-of-life improvement for anyone using MCP servers that have dynamic tools. I took a look through the latest...

I proposed a potential high-level architectural plan that outlines how to implement this in my issue #4897 . Feedback is appreciated.