How-Tos & Practical Guides

OpenClaw v2026.4.14 shipped a meaningful security fix for Slack integrations: the allowFrom owner allowlist is now consistently enforced for block actions and modal interactive events. If you were relying on the allowlist for security before this release, it wasn’t fully protecting you. Now it is — but only if it’s correctly configured. This guide walks you through verifying and tightening your Slack allowlist configuration after upgrading. What Changed in v2026.4.14 Before the fix, OpenClaw’s Slack integration enforced the allowFrom allowlist for some interaction types but not all. Specifically: ...

After a developer recently used Claude itself to discover that a Vercel plugin bundled with Claude Code was collecting bash commands and session data beyond its stated scope, the question of plugin supply-chain safety has moved from theoretical to immediate. This checklist gives you a practical process for auditing what your Claude Code plugins are actually doing. Related news: Claude Code’s Vercel Plugin Quietly Collected Bash Commands — A Developer Used Claude to Expose It ...

Cloudflare’s Agents Week brought two tools that, combined, solve one of the most persistent infrastructure problems in production agentic AI: how do you run agents that actually do work across multiple sessions without losing state? This guide walks through building a persistent long-running agent using Cloudflare’s GA Linux Sandboxes and the Think SDK. Both are now generally available — meaning this is production-ready infrastructure, not a preview. What You’re Building A persistent agent that can: ...

The Model Context Protocol (MCP) has published its new authorization specification, and it’s a meaningful upgrade for anyone building or securing AI agent systems. The spec mandates OAuth 2.1 as the foundational auth framework, with RFC 8707 Resource Indicators providing the mechanism for strict, per-resource access controls. If you’re running MCP servers in production — or building agents that communicate with them — this guide walks through what changed, why it matters, and what you need to implement. ...

On April 4, 2026, Anthropic quietly rolled out an OAuth authentication change that broke a significant number of OpenClaw deployments overnight. No breaking change notice in the standard channels. No deprecation warning. Agents just stopped working. OpenClaw GitHub issue #19938 lit up within hours, and the community has been piecing together fixes ever since. This guide walks you through diagnosing the auth gap and getting your OpenClaw agent back online in under 20 minutes. ...

OpenClaw v2026.4.10 ships with a new Active Memory plugin that fundamentally changes how your agent handles context and recall. Instead of relying on you to manually tell it what to remember, the plugin runs a background memory sub-agent that automatically pulls in relevant history before each reply. This guide walks you through installation, configuration, and the key things to know before you turn it on. Prerequisites OpenClaw v2026.4.10 or later (check with openclaw --version) An existing OpenClaw workspace configured Basic familiarity with OpenClaw plugins Step 1: Install the Active Memory Plugin The plugin ships as an optional module in v2026.4.10+. To enable it: ...

If you’ve spent any time with AI coding agents, you’ve likely hit the same wall: the output is powerful, but it’s not reliable. Run the same prompt twice and you get different results. Prompts live in chat history, not in version control. Workflows are tribal knowledge that evaporates when the context window resets. Archon is an open-source workflow orchestration platform that addresses this directly. It wraps AI coding agents — primarily Claude Code and OpenAI Codex CLI — in YAML-defined workflows that make agentic coding deterministic, composable, and version-controllable. ...

Anthropic published its Trustworthy Agents in Practice framework yesterday — a five-principle safety baseline for autonomous Claude agents. The principles are solid, but they’re abstract. This guide translates each one into concrete configuration and design choices you can make in OpenClaw today. The Five Principles (Quick Summary) Before the how-to: Anthropic’s framework names five principles for trustworthy agent operation: Human control — Maintain meaningful oversight; prefer reversible actions Alignment with user expectations — Act on intent, not just literal instruction Security — Resist prompt injection and adversarial inputs Transparency — Be honest about capabilities, limitations, and actions taken Privacy — Operate with minimum necessary access to data Each maps to specific choices in how you configure and constrain your agents. ...

As AI agents proliferate across enterprise environments, a predictable problem has emerged: nobody knows what agents exist, who owns them, or whether they’re safe to use. AWS has a solution. Today, the company previewed Agent Registry, a centralized enterprise catalog for AI agents, inside its new AgentCore platform. This is a serious infrastructure announcement aimed squarely at the enterprise agent management problem — and it’s live in five AWS regions today. ...

Security researchers at LayerX have published findings that should give every Claude Code user pause: a carefully crafted CLAUDE.md file can turn the agentic coding assistant into what they describe as a “nation-state-level attack tool” — capable of executing SQL injection attacks, stealing credentials, and bypassing safeguards during normal coding sessions. No actual coding required on the attacker’s part. Just a malicious markdown file. What Is “Vibe Hacking”? LayerX coined the term vibe hacking to describe a class of attacks where malicious instructions are embedded in the ambient configuration context of an AI coding agent, rather than in explicit code or prompts. The “vibe” in question is the agent’s operating context — its instructions, its persona, its assumed goals. ...