Topic
206 articles found
Building a Complete Developer Terminal Setup for Claude Code — Part 2: Custom Statusline By Avinash, GenAI Practice Lead | Part 1 | Part 2 of 6 ⚠️ Note: This setup is macOS-specific. All tools, commands, and configurations in this series are tested on macOS (Apple Silicon). Linux and Windows users w
Originally published at recca0120.github.io }}">Two weeks ago I scanned 95 days of Claude Code logs and found that since 4/9, sub-agents had been 100% downgraded to 5m TTL — 5 consecutive days, 4,840 API calls, with the main agent completely untouched. I left the conclusion at "monitoring," since 5
Claude Code Billing Alert, Workflow Enhancements & Open-Source OCR Benchmarks Today's Highlights Today's highlights include a critical billing bug affecting Claude Code users, a comprehensive cheat sheet for optimizing Claude Code workflows, and the release of DharmaOCR, an open-source 3B SLM with s
https://agent-rail.dev/blog/claude-code-enterprise-production-risks Claude Code can deploy code, merge pull requests, and modify production systems autonomously. Here's what enterprise teams need to govern before deploying it at scale. Claude Code is one of the most capable coding agents available t
If you've ever set up Netdata, you know that feeling — hundreds of real-time charts, per-second granularity, metrics you didn't even know your kernel exposed. It's a wonderful piece of software, genuinely one of the best open-source monitoring tools out there. But here's the thing: I run a small fle
Claude Code: Hooks, Subagents, and Skills — Complete Guide Claude Code offers three extensibility layers: hooks for lifecycle automation, subagents for parallel task delegation, and skills for reusable prompt templates. This guide explains each mechanism, when to apply which, and how to combine them
You type one line into Claude Code and hit Enter. In the background, ~80 KB of JSON gets shipped to Anthropic. System prompts, tool definitions, your CLAUDE.md, the full conversation history — all of it, every single request. The interesting part isn't the size. It's what's inside, why it's structur
Three problems hindered Claude Code over the last month.
Anthropic’s Claude Code regression postmortem is unusually specific. In an April 23 engineering note, the company said three vendor-side changes made Claude Code feel worse for users, while the API and inference layer were not impacted. That distinction matters. This was not Anthropic saying the und
Coding agents are like absent-minded professors, this fixes that gap
Your hooks run shell scripts. Every time a hook needs to call an MCP server, it spawns a subprocess, wires up transport, handles auth, parses the response, and formats JSON back to stdout. For a security check that fires on every file write, that overhead adds up fast. As of Claude Code v2.1.118, th
Learn how to get the most out of Claude Code The post How to Improve Claude Code Performance with Automated Testing appeared first on Towards Data Science.
I used to dread production bugs. Not because they were always hard to fix, but because finding them felt like forensic archaeology. Grep through logs. Check git blame. Try to reconstruct what state the app was in when it broke. Two hours to find a three-line fix. That changed when I started using Cl
Anthropic has acknowledged complaints regarding Claude Code's performance, attributing issues to three updates that affected coding quality.
The accidental sprawl I wanted to know how many Claude Code agents I had accumulated. The answer was uncomfortable: $ ls ~/.claude/agents/ | wc -l 47 Plus 7 slash commands, 18 CLAUDE.md memory files scattered across project directories, and a handful of skills. Seventy-two artifacts total, and no cl
Claude Code became far more useful once I stopped treating it like a code generator and started using it to understand projects and terminal chaos.
LLM OCR Benchmarks, Claude Code Context Issues, & Cloud GPU Pricing Tool Today's Highlights Today's highlights include an open-source framework benchmarking LLMs for OCR, revealing cost-saving potential with older models. Additionally, deep technical issues with Claude Code's context management have
A Turkish version of this post was originally published on blog.arasmehmet.com. Disclaimer: All source code referenced is property of Anthropic. This analysis is based on the publicly shipped npm package artifact. No proprietary code has been redistributed. March 31, 2026. Anthropic's npm package @a
I was halfway through writing this post when I decided to fact-check myself. Opened ~/.claude/settings.json, expecting three or four hooks I'd forgotten about. There was one. A Stop hook that plays a ding and says "your turn" when Claude finishes thinking. My hooks-to-skills ratio: 1 to 42. I'm not
Lunes por la mañana. Abro Timeview — mi gestor de tareas — y hay un ticket nuevo: migrar un listado de scroll virtual a paginación tradicional. Hace unos meses, este momento significaba 10 o 15 minutos de fricción antes de poder siquiera pensar en el cambio. Copiar el título, crear la issue en GitLa
