Claude Report — 2026-05-27

🚀 Anthropic Official

Claude Code v2.1.152

• /code-review --fix applies review findings directly to the working tree; /simplify is now an alias for /code-review --fix
• Skills and slash commands accept disallowed-tools in frontmatter to strip tools from the model while the skill is active
• New /reload-skills command re-scans skill directories without restarting the session
• SessionStart hooks can return reloadSkills: true to trigger a skill re-scan, and can now set the session title via hookSpecificOutput.sessionTitle
• New MessageDisplay hook event lets hooks transform or suppress assistant message text before display
• Auto mode no longer requires opt-in consent
• Vim mode: / in NORMAL mode opens reverse history search; thinking summaries cap at 10 lines and stay visible for at least 3 seconds

Anthropic opens Seoul office; KiYoung Choi named Representative Director for Korea

Choi joins from Snowflake (former GM, Korea) with 30+ years of tech leadership; Seoul is Anthropic's third APAC hub after Tokyo and Bengaluru. Korea ranks top 5 globally in both total and per-capita Claude usage, with weekly active Claude Code users growing 6x over four months.

🔌 Claude Code Plugins

Plugin tracking skipped this execution (top-10 install cache not loaded; individual plugin folder changes in anthropics/claude-plugins-official could not be verified against the ranked list).

🛠️ Skills

None of the top 5 updated in window.

Unchanged in window: brainstorming, systematic-debugging, test-driven-development, subagent-driven-development, writing-plans

🤖 Agents & Subagents

None of the top 5 updated in window.

Unchanged in window: VoltAgent/awesome-claude-code-subagents, wshobson/agents, anthropics/claude-plugins-official agents, milisp/awesome-chatgpt-claude-agents, rahulvrane/awesome-claude-agents

🔗 MCPs & Integrations

None of the top 5 updated in window.

Unchanged in window: modelcontextprotocol/servers, steipete/claude-code-mcp, mcp-server-filesystem, mcp-server-puppeteer, anthropic-mcp-connector

💡 Community — Workflows & Ideas

Claude Code as a Daily Driver: CLAUDE.md, Skills, Subagents, Plugins, and MCPs

Published May 26; reached HN front page (64 points, 34 comments). Treats Claude Code as a configurable agent system where CLAUDE.md/CLAUDE.local.md are primary levers, skills encapsulate reusable logic, and every mistake becomes a documented rule — core thesis: "the setup is the work."

📰 Quick Mentions

Relevant links that don't warrant a section of their own:

• anthropics/claude-plugins-official — security-guidance update — May 26 commit updates the security-guidance plugin; detailed diff not public but user-facing guidance content changed