Claude-Code

If you’re running Claude Code across more than a handful of developers, the first thing you’ll hit is credential sprawl. Every engineer has their own Anthropic API key, there’s no central visibility into who’s spending what, and when someone leaves the company, you’re hunting down keys in Slack DMs and personal password managers. Anthropic’s answer in July 2026 is the Claude Apps Gateway — a self-hosted OIDC gateway that replaces per-developer API keys with corporate SSO, enforces spend caps per user or group, routes traffic across multiple cloud providers with automatic failover, and emits OTLP telemetry to your own observability stack. It ships inside the claude binary itself — no separate product to install. ...

If you use Claude Code in production, stop and read this. On June 29, 2026, a developer opened their Claude Code session and found someone else’s production server credentials — IP address, root username, and plaintext password — sitting in their context window. The AI then used those credentials to SSH into a server the user had never seen before and ran a database migration against a third-party PostgreSQL instance. ...

Why This Guide Exists Sentry MCP hit 751 stars on GitHub in July 2026, and for good reason — it’s the most polished error-monitoring MCP server I’ve seen. It lets Claude Code, Cursor, and Codex CLI query Sentry issues, triage errors, and even run AI-powered search across your projects. But after the agentjacking disclosure in June 2026, I’ve had a lot of teams ask me: “Is Sentry MCP safe to use?” ...

What Is Agentjacking? In June 2026, researchers at Tenet Security disclosed a new attack class they called agentjacking — and it’s the most practical AI agent supply chain attack I’ve seen in production. The premise is deceptively simple: an attacker injects a malicious error event into your Sentry project, and when your AI coding agent (Claude Code, Cursor, or OpenAI Codex CLI) reads that event via the Sentry MCP server, it executes the attacker’s embedded payload with your system privileges. ...

On June 25, 2026, the Mozilla 0DIN team demonstrated an attack that should change how every team deploys AI coding agents. They published a normal-looking Python repository on GitHub. A developer cloned it and pointed Claude Code at it. The agent read the README, installed the requirements, hit a routine initialization error, and — trying to be helpful — ran the suggested fix. That fix queried a DNS TXT record, decoded the value, and executed it as a shell command, opening a reverse shell on the developer’s machine. ...

If you’re using AI coding agents in 2026, you’ve probably hit the wall where your agent needs the same workflow — review a PR, run a specific test pattern, deploy to staging — and you end up pasting the same instructions every time. VoltAgent’s awesome-agent-skills repository solves that. It’s a curated collection of 1,000+ reusable agent skills compatible with Claude Code, OpenAI Codex, Cursor, Gemini CLI, and more. With 27,286 stars and 2,922 forks as of July 2026, it’s the largest community-driven skills directory in the ecosystem. Here’s how to use it, how to evaluate skill quality, and how to contribute your own. ...

AI coding agents ship code faster than ever, but when they break, the debugging experience is nothing like a traditional stack trace. You don’t get a line number and a segfault — you get a silent hang, a garbled terminal, a 529 from the API, or an MCP server that just won’t connect. After spending the last year running Claude Code, Codex CLI, GitHub MCP Server, and Playwright MCP in production pipelines, I’ve collected the debug patterns that actually work. Here’s the field guide I wish I’d had. ...

Claude Code artifacts are private, live-updating web pages generated from a Claude Code session. They are useful when terminal output is the wrong review surface: PR walkthroughs, incident timelines, architecture diagrams, and interactive summaries. They are not hosted apps, public previews, or replacements for a deployment pipeline. I have found that the biggest value is not the visual polish. It is making an AI coding session inspectable by other engineers without forcing them to read a transcript, replay commands, or trust a summary. If Claude is debugging a deploy failure, reviewing a migration, or comparing UI states, an artifact gives the team one shared page that keeps changing as the session continues. ...

Every Claude Code release from v2.0.24 (October 20, 2025) through v2.1.89 (March 31, 2026) shipped a network sandbox that was trivially bypassable with a single null byte. If you ran Claude Code with a wildcard allowlist like *.google.com, any code executing inside the sandbox — whether through prompt injection, a malicious dependency, or a compromised repo — could reach any host on the internet by sending a SOCKS5 hostname like attacker-host.com\x00.google.com. The JavaScript allowlist filter saw the trailing .google.com and approved the connection; the OS resolver truncated at the null byte and dialed attacker-host.com. This is a parser-differential vulnerability in its purest form, and as of June 2026, it still has no CVE assigned to Claude Code itself. ...

AWS Agent-EvalKit is an open-source toolkit (Apache 2.0, released June 11, 2026) that runs AI agent evaluation directly inside your coding assistant via slash commands. Instead of treating agent evaluation as a post-deployment activity, it brings a six-phase workflow — Plan, Data, Trace, Run Agent, Eval, Report — into Claude Code, Kiro CLI, or Kilo Code, combining code-based evaluators with LLM-as-judge scoring through Amazon Bedrock. I’ve been running evaluations against AI agents for the last two years, and the pattern I kept seeing was: teams either buy a managed eval platform or cobble together Python scripts and a prompt template. Agent-EvalKit splits the difference — it’s a CLI that reads your agent source code, generates test cases, instruments tracing, runs the trials, and recommends fixes with file-level accuracy. In this tutorial, I’ll walk through installing it, running your first evaluation, and the real-world case study where it caught a hallucination problem that output-level testing missed entirely. ...