How-Tos & Practical Guides

Claude Code’s latest release (v2.1.9x) adds initialPrompt — a YAML frontmatter field that auto-submits a first turn when a subagent is spawned. This guide shows you exactly how to use it. What You’ll Accomplish By the end of this guide, you’ll have subagents that start executing immediately when invoked — no manual prompting required. Prerequisites Claude Code v2.1.9x or later (claude --version to check) An existing Claude Code project with at least one subagent definition Basic familiarity with YAML frontmatter in agent files Step 1: Update Claude Code First, make sure you’re on the latest version: ...

CVE-2026-33579 is a critical privilege escalation vulnerability in OpenClaw (CVSS 8.1–9.8) that allowed anyone with operator.pairing scope — the lowest permission level — to silently grant themselves full admin access. It was patched in v2026.3.28, but the exploit leaves no obvious trace. Security experts recommend that any OpenClaw instance running a pre-patch version should be treated as potentially compromised, even without visible evidence of breach. This checklist walks you through the full audit process. ...

CVE-2026-32211 is a CVSS 9.1 information disclosure vulnerability in Azure MCP Server. Missing authentication allows unauthenticated attackers with network access to read sensitive data — API keys, agent tokens, and data source credentials the MCP server manages. No credentials required to exploit. No prior access needed. This guide walks through the immediate mitigation steps while an official patch is pending, and the longer-term hardening practices that should apply to any MCP server deployment. ...

If you’re running OpenClaw on any version before 2026.3.28, stop reading and go update. Right now. We’ll be here when you get back. For everyone else: here’s what happened, why it’s serious, and exactly how to verify you’re protected against two freshly disclosed critical vulnerabilities: CVE-2026-33579 and CVE-2026-34426. What Are These Vulnerabilities? CVE-2026-33579 — Privilege Escalation via /pair approve (CVSS 8.1–9.8) This is the big one. Rated between 8.1 and 9.8 out of 10 on the CVSS scale, CVE-2026-33579 allows an attacker who holds operator.pairing scope — the lowest meaningful permission in an OpenClaw deployment — to silently approve device pairing requests that ask for operator.admin scope. ...

Running multiple AI coding agents in parallel is one of the most powerful productivity patterns available to developers in 2026. But it comes with a painful problem: agents working on the same Git repository step on each other. File conflicts. Race conditions. One agent’s changes overwriting another’s mid-task. Oh My Codex — a Git worktree automation toolkit that surged to 2,867 GitHub stars after its March 15 release — solves this problem cleanly. It automates the creation and management of isolated Git worktrees for each agent, so you can run Claude Code, Cursor, or any other coding agent in genuine parallel without conflicts. ...

The Claude Code source code leak of March 31, 2026 created an immediate security hazard: threat actors began distributing Vidar infostealer malware through convincing fake GitHub repositories within 24 hours. If you’ve cloned any Claude Code fork from an unofficial source since then, this guide is for you. This is a practical, step-by-step walkthrough for: Verifying whether you downloaded a legitimate or fake Claude Code repo What to do if you ran a malicious installer How to protect yourself going forward Step 1: Verify the Repository You Downloaded Check the GitHub organization The only legitimate Claude Code repository is under the official Anthropic GitHub organization: ...

The CertiK study published today identified 135,000 internet-exposed OpenClaw instances with systemic security failures: authentication disabled, API keys in plaintext, malware in the skills store. Most of those deployments weren’t the result of malicious intent — they were the result of setting up OpenClaw following the default quick-start guide and then opening it to the internet. This guide is the one you should follow instead. It covers a complete, production-grade VPS deployment of OpenClaw v2026.4.1 with the security hardening necessary to run it safely on a public-facing server. ...

If you’ve been hitting Claude Code’s usage limits in 20 minutes instead of hours, you’re not imagining it and you’re not alone. The developer community has named it Cache-22: a prompt cache regression in recent Claude Code versions that’s causing Max-tier quotas to exhaust dramatically faster than expected. Anthropic has acknowledged the bug. A fix is in progress. In the meantime, here’s how to work around it. What’s Happening Prompt caching is supposed to save tokens by reusing previously-processed context instead of re-processing it from scratch every request. When it works correctly, it dramatically extends how far your token quota goes — particularly in agentic workflows with large context windows. ...

Today’s Claude Code source leak was a good reminder that shipping to npm is a security surface area that many developers don’t audit carefully enough. A 60MB .map file contained Anthropic’s entire CLI source. This guide shows you how to prevent the same thing from happening to your own packages. Why Source Maps Are the Hidden Risk Source maps (.js.map files) are generated by build tools like webpack, esbuild, Rollup, and Parcel to help with debugging. They map your compiled, minified output back to the original source. In development and CI, this is exactly what you want. ...

The “token tax” problem is real. As enterprises and power users deploy OpenClaw at scale, a recurring nightmare scenario is playing out: you set up an autonomous reasoning loop before bed, wake up, and discover your OpenAI or Anthropic bill has ballooned by $500–$1,000+ overnight. This is not a hypothetical. It’s being reported across the OpenClaw community today — in Paul Macko’s OpenClaw Newsletter, on ManageMyClaw.com, and in cost guides circulating in developer channels. And the root cause is straightforward: OpenClaw ships with no native API rate limiting or daily spend caps by default. ...