AI Briefing#claude-code
The latest AI and developer news about #claude-code, with the original source and a short summary.
The latest AI and developer news about #claude-code, with the original source and a short summary.
The shortened Claude Code cache TTL caused a sharp spike in cache regeneration costs and quota consumption.
A cache_read calculation error in the Pro Max 5x plan causes quota to be consumed rapidly.
xAI is preparing credit-based billing with monthly allocations and additional purchases for Grok Build.
Anthropic is redesigning Claude Code desktop to strengthen parallel agent workflows.
Someone built a local virtual pet that shows token usage in the Claude Code status line.
Claude Code built a multi-manager portfolio using internal portfolio data.
An open-source memory system with 29 Python scripts and a zero-dependency design that survives compaction was released.
A plugin that publishes Claude Code conversations publicly with a single command.
A 10-year QA veteran launched a Ukrainian cultural events aggregator in 7 days using Claude Code.
A tool that wraps Claude Code in tmux and xterm.js to control long-running workflows.
An analysis suggests that Claude Code's cache TTL changed from 1 hour to 5 minutes.
Hand off CLI plans to the cloud to refine and run them on the web.
TLDR is looking for a senior engineer to automate internal work with AI agents and Claude Skills.
Built a family-friendly AI DM for D&D using a Claude Code skill that even casts to a TV.
Claude Opus 4.6 has launched with enhanced coding, long-context, and safety capabilities.
Claude Sonnet 4.6 significantly improves coding, computer use, and long-context reasoning across the board.
Claude Code has added an event-waiting Monitor that reduces polling loops.
Shopify has released the **Shopify AI Toolkit**, which supports AI agents in building and operating online stores.
Claude Code has introduced a Monitor Tool feature that uses background processes to operate only in specific situations.
A semantic knowledge base for Claude Code cut code comprehension cost from 83k tokens to 3.7k.
This summarizes how to design AI not as a personal prompt but as a team development architecture.
An open-source skill that automatically analyzes Claude Code's mistakes and fixes them with rules and hooks.
As coding agents take on deployment and operations, infrastructure itself is being reorganized around agents.
Combined LLM Wiki with MemPalace MCP to implement cross-session memory for Claude Code.