A developer is building Loupe, a platform for practicing the skill of finding bugs in AI-generated code. The project was inspired by the realization that AI coding agents often produce code that passe…
NVIDIA released SkillSpector, an open-source security scanner designed to detect malicious code in AI agent skills before installation. The tool runs a two-stage pipeline combining static analysis wit…
Anthropic's Claude Code 2.1.183, released June 19, blocks eight destructive shell commands in auto mode, including `terraform destroy` and `git reset --hard`, after an AI agent wiped a production data…
A Hacker News user asks whether switching from Codex to Claude Code with Fable 5 is worthwhile, with one commenter affirming the switch.…
Anthropic released an open-source skill for Claude Code called launch-your-agent that enables technical founders to build and deploy self-grading agents in a single conversation. The skill uses an int…
A developer building with Claude Code discovered that AI task execution can be significantly sped up by splitting independent modules and running multiple agents in parallel. The approach requires a l…
A developer building AgentLeash argues that as AI coding agents like Claude Code, Cursor, and Codex become more autonomous, the bottleneck shifts from code generation to supervision and control. They …
Agent-historian, a new open-source CLI tool, lets AI coding agents search their own past conversation history from the command line, enabling them to recover prior research, commands, errors, and deci…
An engineer at Anthropic shares a setup guide for Claude Cowork, emphasizing that the tool works best with a delegation mindset rather than chat-style prompting. Key recommendations include creating d…
A developer built ccglass, an open-source local proxy and dashboard that lets engineers inspect the full request flow of AI coding agents, including system prompts, tool call schemas, tool results, pe…
A developer warns that connecting an MCP server to an AI coding agent introduces two distinct security threats: the agent executing destructive commands and the agent being manipulated by untrusted da…
A new open-source tool called cc-fleet enables Claude Code to use third-party large language models as workers, allowing users to run models from providers like DeepSeek, GLM, Kimi, and Qwen within Cl…
Z.ai's GLM-5.2 model was claimed to rank No. 3 on Agent Arena and beat Google's Gemini 3.5 Flash, but the claim lacks context as Agent Arena is a live, multi-signal leaderboard where rankings vary by …
Rocannon, a new open-source tool, converts any installed Ansible module or role into a typed MCP (Model Context Protocol) tool, enabling AI assistants like Claude Code and Cursor to drive real infrast…
Rlsgate, a new open-source CLI tool, blocks Supabase Row Level Security leaks before deployment by scanning local migrations, policies, and env files for critical vulnerabilities like the CVE-2025-487…
Anthropic's Claude Opus 4.7 autonomously completed robotics tasks 20 times faster than the fastest human team in a follow-up to Project Fetch, demonstrating rapid AI progress in physical-world tasks. …
JP Hutchins implemented webmentions and Fediverse federation on their static blog using Claude Code to generate a plan from existing resources, enabling comments and cross-posting. The site now federa…
A Princeton team's CoALA framework defines four types of memory for AI agents—working, semantic, procedural, and episodic—and Claude Code implements each as plain files and commands rather than a vect…
Library authors can ship AI agent skills inside NuGet packages, automatically installing them when developers add the library. This approach, demonstrated by the StructId and Mockly libraries, improve…
Cisco Foundation AI open-sourced FAPO, a Claude Code-driven system that autonomously optimizes multi-step LLM pipelines by attributing failures at the step level and proposing variants. In evaluations…