Claude Code v2.1.119 shipped multi-VCS support for –from-pr (GitLab, Bitbucket, GitHub Enterprise), settings persistence to ~/.claude/settings.json, and proper agent frontmatter handling in –print mode. A release that reads like a feature patch but signals something bigger about where Claude Code is heading.
The 2026 AI Coding Impact Report reveals that 100% of engineering orgs are shipping more code thanks to AI — and security teams are drowning. 92% of AI-generated codebases contain critical vulnerabilities. The answer isn’t less AI. It’s better AI review.
Claude Code v2.1.118 ships vim visual mode, a full custom theming system, and hooks that can now invoke MCP tools directly. Small-sounding updates that collectively make Claude Code meaningfully more extensible — and more comfortable for developers who live in the terminal.
OpenCode has 147K GitHub stars, 6.5M monthly developers, and supports 75+ LLM providers. Here’s an honest look at what it gets right, where it falls short, and when it makes more sense than Claude Code.
You gave Claude Code to 40 engineers. Now everyone’s writing their own prompts, their own workflows, their own shortcuts. Here’s how one team turned that chaos into a shared skill marketplace — and what they learned building it.
The benchmark releases get the press. The unglamorous power-user features don’t. Here’s what /ultrareview, auto mode for Max, xhigh effort, /recap, and the new prompt caching TTL controls actually change about your daily Claude Code workflow.
Anthropic’s Claude Code Analytics API gives enterprise organizations programmatic access to daily aggregated usage metrics — commits, PRs, lines of code, session counts, token costs, and more — per developer, per day. Here is what it tracks, how to set it up, and why it matters for every team that needs to justify its AI coding investment to leadership.
Most developers use a fraction of what Claude Code can do. Two new commands shipped in v2.1.90 — /powerup and /insights — attack this problem from opposite ends: one teaches you what’s possible, the other shows you where your actual workflow breaks down.
A patched vulnerability in Claude Code (CVE-2026-21852) reveals an entirely new attack surface: poisoned project config files that silently bypass your deny rules and exfiltrate credentials. Here’s what happened, how the exploit works, and what it means for agentic security.
Nine agentic coding agents benchmarked and compared as of October 1, 2026. Anthropic shipped Opus 5.5 (Sept 22) and Sonnet 5.5 (Sept 28) since the last update, and Claude Code Projects entered beta Sept 17; the benchmark table below still carries the last independently verified numbers, with newer third-party claims flagged rather than folded in. Updated biweekly.