Juan Andrés Núñez.

Senior Frontend Engineer specializing in Agentic AI, professional educator and speaker. Where engineering meets humanism.

Juan Andrés Núñez
Focusing on
Building FrontendLeap: teaching how to build the professional Web with GenAI and learning science.
Claude Code

Claude Code: from zero to professional. Tips, tutorials and deep dive guides from an engineer who uses it 12 hours a day.

Explore the hub
Claude Code Tips View all →
#090

Security in Claude Code: make it catch its own vulnerabilities before they hit prod

An official plugin puts Claude to work reviewing its own code for vulnerabilities as it writes, and fixing them in the same session. The earliest security layer: it catches the flaw in the editor, not in the PR.

#089

ultracode in Claude Code: let Claude decide on its own when to deploy an army of agents

There are two ways to get agents out of Claude Code: you decide when, or Claude does. `/effort ultracode` is the second, and it changes how your whole session works. When to flip it on, what it costs, and how to switch back.

#088

Claude Code channels beyond chat: push CI, deploy, and error events into your live session

The best-known use of channels is chat, but at heart it's an event receiver: your CI, Sentry, or a deploy can push a webhook into the Claude Code session you already have open. The chat plugins ship ready-made; the webhook receiver is a ~30-line MCP server.

#087

/diff in Claude Code: inspect what Claude touched on every turn, without leaving the terminal

Popping out to `git diff` to see what Claude touched? There's a native viewer right in the terminal — and its per-turn view doesn't come from git, but from the conversation itself.

Gravitas

Get only what matters

If I have nothing worth saying, you won't hear from me. When I do, you'll be the first to know. 7,000+ people already trust this.

Are you a professional Web developer?
No

Unsubscribe at any time.