Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The post frames model routing — not prompting — as the primary productivity lever in Claude Code, and provides a concrete cost-and-capability breakdown of five distinct models that developers must now choose between for every task.
The post demonstrates a concrete path from single-agent discipline to parallel multi-agent orchestration, showing how the author's own role contracted from writing code and reviews to tuning workflows — a practical illustration of what the "conductor" layer of agentic development looks like in practice.
The post provides concrete token-level billing data showing that cache management — not raw prompt length — is the dominant cost lever when using Claude Code at scale, with an 86.4% cache hit rate cutting what would otherwise be a far larger bill.
The post consolidates the practical attack surface of agentic coding workflows — prompt injection, credential exposure, and permission creep — into a single set of concrete defensive habits, grounding each in the specific ways Claude Code's file, shell, and tool access can be exploited.
Z Code gives developers a free, high-capacity alternative to Codex — 5 million tokens per day — backed by GLM-5.2, currently the top-ranked open-weights model on the Artificial Analysis Intelligence Index, under a permissive MIT license.
Claude Code's new HTML deployment capability extends Artifacts from a single-user output format to a shareable team communication tool for architecture, analysis, and prototyping work.
The remote session feature extends an active IntelliJ coding session to a mobile device without interruption, while the new debug logs and token visibility give developers direct insight into how Copilot's agentic decisions are made.
The incident demonstrates that `--dangerously-skip-permissions` removes human oversight entirely rather than merely reducing friction, and that `.claude/settings.json` deny rules provide a harder enforcement boundary than confirmation prompts or `CLAUDE.md` instructions alone.
cwcode's hash-anchored edit scheme and sticky prefix-cache design directly cut token costs and output volume compared to naive agent loops, making sustained multi-hour autonomous coding runs on local or low-cost LLM endpoints practical without any cloud service dependency.
The post demonstrates that in multi-agent fanout pipelines, context assembly before the LLM call — not the LLM itself — can become the dominant latency and cost driver, and that passing only compact summary structs rather than full subagent outputs resolves both problems simultaneously.