ClawDocx Blog
Claude Code tutorials, OpenClaw setup guides and AI agent analysis for 2026: sub-agents, hooks, CLAUDE.md, skills, local models and security.
Latest
Anthropic's 2026 Usage Policy update: what changes for people building agents
Anthropic published its 2026 Usage Policy on 8 October, effective 12 November. The sections that change what an agent may do, and what stays the same.
Are agent skills safe? What a SKILL.md can reach, and how to check one
A skill is instructions plus code that runs with your agent's own authority. What a SKILL.md can reach on each platform, and how to check one.
Is Meta Muse safe? Secure VM, Sentinel and approvals explained
Meta Muse runs in an isolated VM where a Sentinel approves every action and the agent never sees real credentials. What that covers, and what it misses.
Hermes Agent vs OpenClaw: which self-hosted agent should you run in 2026?
Hermes Agent and OpenClaw are both MIT-licensed self-hosted agents. Compare their hardware support, skills, MCP, costs and the one-way migration path.
Claude Code now runs mods: what they change and what they can reach
Anthropic shipped mods in Claude Code v2.1.287 on 1 October 2026. They run inside the agent with your permissions, unsandboxed, and here is what they reach.
What is MCP? A plain-English guide to the Model Context Protocol
MCP is an open standard that lets AI apps connect to outside tools and data. What it is, how hosts and servers talk, who runs it, and what 2026-07-28 changed.
Cursor vs Claude Code vs Copilot (2026): Agents, Skills and Pricing
How Cursor, Claude Code and GitHub Copilot compare in 2026 on agent surfaces, skills folders, model access and the prices each vendor publishes.
Codex vs Claude Code (2026): pricing, limits, skills and config
Codex and Claude Code compared on documented plans, usage limits, where skills live and which config files each one reads, with a source for every figure.
Claude Code skills vs subagents vs plugins vs MCP servers: what to use when
Skills, subagents, plugins and MCP servers solve four different problems in Claude Code. Here is where each one lives, what loads it, and how to choose.
News & Insights
All 26 postsAnthropic's 2026 Usage Policy update: what changes for people building agents
Anthropic published its 2026 Usage Policy on 8 October, effective 12 November. The sections that change what an agent may do, and what stays the same.
Claude Code now runs mods: what they change and what they can reach
Anthropic shipped mods in Claude Code v2.1.287 on 1 October 2026. They run inside the agent with your permissions, unsandboxed, and here is what they reach.
Anthropic launches Claude Marketplace: connectors, plugins, agents and partners
Anthropic opened the Claude Marketplace on 23 September 2026, with over 2,000 connectors and plugins, agents you buy with committed spend, and service partners.
Guides & Tutorials
All 24 postsHermes Agent vs OpenClaw: which self-hosted agent should you run in 2026?
Hermes Agent and OpenClaw are both MIT-licensed self-hosted agents. Compare their hardware support, skills, MCP, costs and the one-way migration path.
Cursor vs Claude Code vs Copilot (2026): Agents, Skills and Pricing
How Cursor, Claude Code and GitHub Copilot compare in 2026 on agent surfaces, skills folders, model access and the prices each vendor publishes.
Codex vs Claude Code (2026): pricing, limits, skills and config
Codex and Claude Code compared on documented plans, usage limits, where skills live and which config files each one reads, with a source for every figure.
Getting Started
All 13 postsWhat is MCP? A plain-English guide to the Model Context Protocol
MCP is an open standard that lets AI apps connect to outside tools and data. What it is, how hosts and servers talk, who runs it, and what 2026-07-28 changed.
What is SKILL.md? The Agent Skills standard and which agents support it
SKILL.md is the entry file of an Agent Skills folder. What the spec requires, which agents read it, where each one looks, and how to vet a skill.
Getting Started with Claude Code + OpenClaw: The Complete Setup Guide
Learn how to connect Claude Code to OpenClaw using ACP: run coding sessions from chat, spawn thread-bound agents, and use voice mode, /loop, and hooks.
Tips & Tricks
All 11 posts21 OpenClaw Power User Tricks That Will Change How You Work
21 OpenClaw tricks that move past the basics, from memory hacks to model routing to silent automations, for people who get real work done with their agent.
How I Replaced My Morning Routine with an AI Agent
Every morning my OpenClaw agent delivers a personalized briefing of weather, calendar, email highlights, tasks, and news. Here's how I set it up.
Prompt Engineering for AI Agents: It's Not What You Think
Prompt engineering for autonomous AI agents is fundamentally different from prompting a chatbot. Here's what actually works for agents.
Security
All 6 postsAre agent skills safe? What a SKILL.md can reach, and how to check one
A skill is instructions plus code that runs with your agent's own authority. What a SKILL.md can reach on each platform, and how to check one.
Is Meta Muse safe? Secure VM, Sentinel and approvals explained
Meta Muse runs in an isolated VM where a Sentinel approves every action and the agent never sees real credentials. What that covers, and what it misses.
ClawJacked: The Vulnerability That Proves Your AI Agent Is an Attack Surface
A malicious website could hijack your local OpenClaw agent through a WebSocket flaw. It's patched, but the lessons go way beyond one CVE.
Stories
All 3 postsAn OpenClaw Agent Applied for a Job, Almost Got Hired, and Tried to Create an LLC
An engineer gave his OpenClaw agent autonomy. It decided to search for jobs, apply to positions, and attempt to register a company — all without being asked.
I Gave My AI Agent $100 and 7 Days to Build a Business — Here's What Happened
What happens when you give an OpenClaw AI agent a $100 budget and one week to build a real online business from scratch? We ran the experiment.
How an AI Agent Negotiated an Insurance Claim (And Won)
The incredible true story of an OpenClaw user whose AI agent negotiated an insurance claim entirely via email — and won.
AI Models
All 2 postsAPI Keys Explained: How OpenClaw Connects to LLM Providers
Understand what API keys are, why OpenClaw needs them, how LLM billing works, and how to get keys from Anthropic, OpenAI, and Google.
The Best LLM Models for OpenClaw in 2026: Claude, GPT, Gemini and Open Weights
The best LLM for OpenClaw in September 2026: Claude Sonnet 5 by default, Kimi K2.5 on a budget, Qwen3.6 locally, with current prices and configs.