Anthropic has rolled out a significant update to Claude Code, its AI-powered terminal coding tool, introducing a real-time security-guidance plugin alongside performance improvements that promise a smoother developer experience across the board.
Security Plugin Catches Vulnerabilities in Real Time
The new security-guidance plugin is available to all Claude Code users and can be installed directly from the plugin marketplace using the /plugins command. Once active, it monitors code edits, diffs, and commits in real time, automatically flagging dangerous patterns before they ever reach production.
Under the hood, the plugin uses regex-based pattern matching to detect approximately 25 high-risk vulnerability classes. These include SQL injection, command injection, cross-site scripting (XSS), hardcoded API keys and secrets, insecure deserialization, and improper input validation vulnerabilities that account for a disproportionate share of real-world breaches.
We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.
Available for all Claude Code users. Install from the plugin marketplace (/plugins). pic.twitter.com/LprgC4m6Kf— ClaudeDevs (@ClaudeDevs) May 26, 2026
When a risky pattern is identified, Claude prompts an inline fix within the same coding session, eliminating the need to context-switch to a separate security scanner.
Anthropic’s broader Claude Security platform, which complements the plugin with a deeper AI-driven codebase scanning, traces data flows across files, runs adversarial verification passes on findings, and proposes targeted patches for human review.
Internal data reportedly shows a 30–40% reduction in security-related comments on pull requests since the tool was introduced.
The announcement was shared via the official Claude Developers account on X (formerly Twitter), confirming the plugin is available immediately for all plan tiers.
Bug Fixes and Speed Boost
Beyond security, Anthropic addressed several usability complaints that had accumulated from the developer community. Key improvements include:
Full-screen renderer — eliminates the screen flickering that disrupts long coding sessions.
Faster streamed responses — reduces latency during active code generation and editing.
Clearer error messages — more actionable feedback when Claude Code encounters issues.
Eased rate limits — session caps for Pro and higher plans have been doubled following a compute deal with SpaceX.
Alongside the security features, Anthropic announced a landmark infrastructure deal with SpaceX, gaining access to the full compute capacity of the Colossus 1 data center in Memphis, Tennessee. The agreement provides over 300 megawatts of new capacity, equivalent to more than 220,000 NVIDIA GPUs, coming online within weeks.
Early reception from the developer community has been largely positive. Users noted the UI now feels noticeably more fluid, and the security plugin integrates without significantly interrupting workflow.
First for our new full-screen renderer (which should get rid of bugs like screen flickering), we’ve made a number of fixes for different environments and terminals.
You can turn it with the command: /tui feedback
We're working on making it the default in Claude Code soon.— ClaudeDevs (@ClaudeDevs) May 27, 2026
Some developers, however, flagged minor UI quirks that remain unresolved, suggesting the update, while substantial, is still iterative rather than a complete redesign.
Anthropic acknowledged the ongoing polish work in its update thread, framing these improvements as part of a broader effort to make Claude Code “more responsive and reliable” as the tool matures in a competitive AI coding assistant market.
The update positions Claude Code more directly against GitHub Copilot and Cursor, both of which have been expanding their own security and performance tooling.
Adding automated vulnerability detection at the diff level is particularly notable it shifts security left into the coding phase rather than relying solely on SAST tools or CI/CD pipeline checks. The security plugin is available now via /plugins inside Claude Code for all users.
Follow us on Google News, LinkedIn, and X to Get More Instant Updates.
The post Anthropic Updates Claude Code With Security Plugin and Faster Performance appeared first on Cyber Security News.
