// edition · 2026-04-04
11 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
Anthropic blocked Claude API access through the OpenClaw platform starting April 4, affecting hundreds of developers running autonomous agents. The incident highlighted concentration risk, as agents built on a single provider and pricing model faced sudden service loss, while those using free tie...
Anthropic's Claude AI assistant offers six pricing tiers ranging from free to enterprise, with Pro at $20/month for baseline usage, Max tiers at $100-200/month for 5-20x usage capacity, and Team plans at $25-30 per seat monthly for group accounts.
Anthropic launched the ClawSouls plugin for Claude Code on April 4, 2026, after removing third-party harness coverage from subscriptions. The plugin allows users to migrate AI agents from external platforms into Claude Code at no additional cost, with features including persona loading, safety sc...
Anthropic will require separate pay-as-you-go billing for third-party tools like OpenClaw starting April 4, no longer covered by Claude subscriptions, citing system strain and capacity constraints.
Xhawk.ai offers a tool that scores codebases for compatibility with coding agents in approximately 30 seconds.
OpenClaw developers patched a high-severity vulnerability (CVE-2026-33579, rated 8.1-9.8/10) that allowed users with pairing privileges to gain administrative control, potentially compromising all resources accessible to the AI agent tool.
Anthropic shipped a source map file containing 512,000+ lines of TypeScript source code in npm package @anthropic/claude-code v2.1.88 on March 31, 2026, which was discovered and reconstructed by security researcher Chaofan Shou, revealing the system's internal architecture including an "undercove...
Anthropic accidentally published a 59.8 MB source map file containing Claude Code's source code in version 2.1.88 of its npm package on March 31, 2026. The debug file, which should never be distributed to end users, exposed internal code structure before being removed.
A Dev.to community discussion asks developers to share what percentage of their code is written by AI and describe their code review processes for AI-generated content.
Daniel Stenberg, lead developer of cURL, reported that AI-generated security reports for open source projects have shifted from mostly low-quality to high volume of legitimate reports, requiring him to spend several hours daily reviewing them.
Vultr launched an Nvidia GPU-powered infrastructure platform that automates developer portal setup using AI agents, claiming 50% to 90% lower costs than major hyperscalers. The system lets platform engineers define security and compliance rules as reusable "skill files" that developers can deploy...
Free daily email. Every story you just read, in your inbox at 6 AM ET.