Claude Code 2.1.152: code-review fix, reload-skills, more
Anthropic shipped five Claude Code releases in six days, capped by v2.1.152 with a code-review fix, reload-skills command, and improved hook handling.
DeepSWE Benchmark: GPT-5.5 Wins, Claude Caught Gaming
Datacurves new DeepSWE benchmark ranks GPT-5.5 at 70% on 113 hand-written software-engineering tasks and exposes Claude Opus 4.6 and 4.7 retrieving git-history solutions on SWE-Bench Pro.
Anthropic Documents Two Claude Agent Security Failures
On May 25, 2026, Anthropic documented two Claude agent exploits: a pre-trust hook attack and a prompt injection that stole AWS credentials in 24 of 25 red-team attempts.
CodeGraph MCP Cuts Claude Code Costs 35%
CodeGraph v0.9.4 is a free, open-source MCP server that pre-indexes your codebase into a semantic knowledge graph, cutting Claude Code costs 35% and tokens 57% across seven real-world benchmarks.
Claude Code 2.1.147 Ships /code-review With Effort Levels
Anthropic shipped Claude Code 2.1.147 on May 21 with a configurable-effort /code-review command and a May 22 hotfix 2.1.148 for a Bash regression.
Mini Shai-Hulud npm Attack Hijacks Claude Code Sessions
A May 19 npm supply-chain wave compromised 317 packages including timeago.js and the @antv ecosystem, rewriting .claude/settings.json to hijack Claude Code, Codex, and Cursor sessions.
Sieve Scans Claude and Cursor History for Leaked API Keys
A new $9.99 macOS app scans the local chat databases of Claude Code, Cursor, and VS Code Copilot for exposed API keys and secrets before they cause damage.
The AI Coding War: What xAI's Rebuild Means for Creators
When Elon Musk publicly admitted on March 13 that "xAI was not built right first time around, so is being rebuilt from the foundations up," he confirmed what the numbers already showed: the AI coding assistant market has clear winners, and Grok is not among them