Links from June 2025
Use ccusage to track your live, daily, and monthly claude code token and dollar usage. In the case of subscription plans it shows you how much you would have paid were you using API. Also estimates your current block usage which you can use to predict whether you’re going to get rate limited at any given time.
Claude code supports remote MCP servers.
plaintextclaude mcp add --transport http github https://api.githubcopilot.com/mcp/ \ --header "Authorization: Bearer <GITHUB_PAT>"
How we built our multi-agent research system speaks to Anthropic’s multi-agent build experiences.
We found that a multi-agent system with Claude Opus 4 as the lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on our internal research eval
However these architectures burn through tokens fast:
In our data, agents typically use about 4× more tokens than chat interactions, and multi-agent systems use about 15× more tokens than chats.
Cognition goes further in Don’t Build Multi-Agents
In some cases, libraries such as swarm by OpenAI and autogen by Microsoft actively push concepts which I believe to be the wrong way of building agents.
a tool that you can use to create and run Linux containers as lightweight virtual machines on your Mac. It’s written in Swift, and optimized for Apple silicon.
After installing and starting the service via container system start the cli gives you a similar experience to docker. Unfortunately in my case after resolving dated sources and switching dependencies to arm64 I discovered my Dockerfile candidate still had an x86 binary so I’ll need to find another candidate to test any performance improvements.