agent registry
30 articles about agent registry in AI news
Stop Building Interfaces: How YC Runs Finance
Claude Code's agent registry model lets non-coders run operations via deterministic tools — YC's 350+ tool ecosystem proves it. Shift from building interfaces to building small tools.
Skills as Untrusted Code: A Security Precedent for Agent Runtimes
Paper argues agent skills are untrusted code until verified; runtimes must enforce verification gates to prevent supply-chain attacks, echoing decades of software security lessons.
Matt Pocock Open-Sources Claude Code Skill Pack for AI Agents
Matt Pocock open-sourced a Claude Code skill pack to improve AI agent behavior. The pack provides curated prompts and configurations for Anthropic's terminal-based coding tool.
From MLOps to AgentOps: A Vision for AI Production in 2026
A forward-looking article argues that by 2026, AI systems will be complex, multi-agent software requiring a new operational discipline called 'AgentOps'. This evolution from MLOps is necessary to manage reliability, safety, and cost at scale.
Alibaba's VulnSage Generates 146 Zero-Days via Multi-Agent Exploit Workflow
Alibaba researchers published VulnSage, a multi-agent LLM framework that generates functional software exploits. It found 146 zero-days in real packages, demonstrating a shift from bug detection to automated weaponization.
Inside Claude Code’s Leaked Source: A 512,000-Line Blueprint for AI Agent Engineering
A misconfigured npm publish exposed ~512,000 lines of Claude Code's TypeScript source, detailing a production-ready AI agent system with background operation, long-horizon planning, and multi-agent orchestration. This leak provides an unprecedented look at how a leading AI company engineers complex agentic systems at scale.
Lowe’s Confronts the Challenge of AI Agent Proliferation
Lowe's is actively managing the proliferation of AI agents within its organization to prevent inefficiency and chaos. This highlights a critical, real-world operational challenge as enterprises scale agentic AI.
AWP (Agent Work Protocol) Launches Testnet on Base, Enabling Autonomous AI Agent Work Coordination
Developer hasantoxr has launched AWP, an open protocol on Base testnet that allows AI agents to autonomously register, find work, and execute tasks without human prompting. The system uses skill files to define work types, enabling gasless agent coordination.
Google Unveils Universal Commerce Protocol (UCP) for Securing Agentic Commerce
Google has released the Universal Commerce Protocol (UCP), an open-source standard designed to secure transactions conducted by AI agents. This framework aims to establish trust and provenance in automated commerce, with direct implications for luxury goods authentication and supply chain transparency.
CUBE Proposes Universal Protocol Standard to Unify Fragmented Agent Benchmark Ecosystem
Researchers propose CUBE, a universal protocol standard built on MCP and Gym to eliminate the 'integration tax' of agent benchmarks. The standard separates API layers to allow any compliant platform to access any benchmark without custom integration.
How Retailers Should Acclimate to Agentic AI
An industry article explores how retailers, including those in furniture and luxury, should prepare for the rise of autonomous AI agents. It highlights a strategic shift from reactive chatbots to proactive systems that can handle complex, multi-step tasks.
Google's gws CLI: The AI-Agent-Ready Tool That Dynamically Masters Workspace APIs
Google has open-sourced gws, a CLI tool that dynamically interfaces with all Google Workspace APIs and ships with built-in AI agent skills. It eliminates custom tooling and automatically adapts to new API endpoints.
Rotifer v0.7.5 Adds Gene Registry & Version Chains — Here's How to Use Them
Rotifer's latest update fixes domain chaos and adds version tracking for genes, plus MCP analytics to see what's actually being used.
How to Manage Skills Across Multiple Repos with a Centralized Registry
Use symlinks and a dispatch skill to share Claude Code skills across projects without plugin namespacing overhead.
How to Build Your Own Claude Code Agent: The Core Loop Explained
Learn the fundamental while-tool-feedback loop that powers Claude Code and how to apply its principles to write better prompts.
Compass v1.1.0 Ships Recall Consumption Fix 12 Hours After Launch
Nautilus-Compass v1.1.0 fixes a recall consumption failure where agents saw file titles but didn't read bodies, embedding body text in top-3 hits and adding a drift detector for unconsumed recalls.
Claude Code Digest — May 31–Jun 03
Claude Code is quietly becoming an operating system: teams are replacing brittle UI layers with deterministic tools, while per-project rules and skills finally make the agent behave like it belongs in the repo.
Claude Code's Six-Layer Architecture: Harness, Not Magic
Claude Code's six-layer architecture uses a 3-layer context compressor at 92% threshold and Redis-based multi-agent FSM protocol. The model is just one node in a harness.
SSL: Structured Skill Language Boosts Skill Discovery MRR to 0.707
Researchers propose SSL, a three-layer typed JSON representation for AI agent skills, replacing unstructured SKILL.md prose. Using an LLM normalizer, SSL improves Skill Discovery MRR from 0.573 to 0.707 and Risk Assessment macro F1 from 0.744 to 0.787 on a newly released 6,184-skill corpus.
The 5-Minute Claude Code Setup: What 'Bare Minimum' Actually Means in 2026
Forget complex configs. The 'bare minimum' Claude Code setup is now just three files: CLAUDE.md, .claudeignore, and a skills registry. Here's how to structure them.
mpesa-mcp: The First African Fintech MCP Server You Can Install Right Now
mpesa-mcp is now on Anthropic's official MCP registry, giving Claude Code access to M-Pesa payments and Africa's Talking SMS.
How Cult of Claude's Directory Lets You Install 3,000+ Skills in Seconds
Cult of Claude aggregates 3,296 skills and 785 agents you can immediately use with Claude Code via simple CLI commands.
AbsolutelySkilled: Install 156 Production-Ready Skills to Make Claude Code Remember Your Conventions
A new registry of structured skill modules (SKILL.md files) lets you install persistent domain expertise into Claude Code once, guiding its behavior across all future sessions.
Claude Code Digest — Jun 03–Jun 06
Claude Code is turning into a workflow OS: teams are replacing brittle UIs with deterministic tools, but the real unlock is making Claude obey project rules instead of freelancing.
TrapDoor supply-chain attack hits npm, PyPI, Crates.io — weaponizes AI config files
TrapDoor planted 34 malicious packages on npm, PyPI, and Crates.io, and injected poisoned AI config files into repos to weaponize Claude Code and Cursor.
From DIY to MLflow: A Developer's Journey Building an LLM Tracing System
A technical blog details the experience of creating a custom tracing system for LLM applications using FastAPI and Ollama, then migrating to MLflow Tracing. The author discusses practical challenges with spans, traces, and debugging before concluding that established MLOps tools offer better production readiness.
Win11Debloat Script Disables Copilot, Recall, Removes Windows AI Bloat
The Win11Debloat script removes Microsoft Copilot, disables the Recall screenshot AI, and strips telemetry and ads from Windows. It highlights user pushback against Microsoft's aggressive AI and data collection integration.
Block Compromised NPM/PyPI Packages Automatically with attach-guard
A new Claude Code plugin uses PreToolUse hooks to automatically block compromised packages like the recent axios hijack before they install.
Anthropic's Claude Skills Implements 3-Layer Context Architecture to Manage Hundreds of Skills
Anthropic's Claude Skills framework employs a three-layer context management system that loads only skill metadata by default, enabling support for hundreds of specialized skills without exceeding context window limits.
Anthropic Scrambles to Contain Major Source Code Leak for Claude Code
Anthropic is responding to a significant internal leak of approximately 500,000 lines of source code for its AI tool Claude Code, reportedly triggered by human error. The incident has drawn attention to security risks in the AI industry and coincides with reports of shifting investor interest toward Anthropic amid valuation disparities with competitors.