· Travis Rodgers · AI
Claude for Chrome: Why It Exists and Is It Safe to Use?
Claude for Chrome lets Claude click, type, and browse for you in your own browser. Here is why it exists, what it does well, and an honest look at whether it is safe.
Tag: agents
· Travis Rodgers · AIIs 1Password for Claude Safe? How It Works and What to Trust
1Password now lets Claude log into websites for you without ever seeing your passwords. Here is how it works, and the one risk it does not cover.
· Travis Rodgers · AIAI Code Is Cheap. Open Source Maintainers Pay the Bill
AI makes code cheap, but open source maintainers still pay for every review. Follow these rules before submitting an AI-assisted pull request.
· Travis Rodgers · AIClaude Code Permission Modes: How to Set Rules That Stick
Claude Code has six permission modes, and yes, deny rules apply to every one of them, even bypass. Here's what each mode auto-approves and how to block commands like rm for good.
· Travis Rodgers · AIMost Agent Skills Are Junk. Here's How to Write a Good One
There are millions of public agent skills now, and a benchmark of 47,150 of them found most barely move the needle. Here is how to spot the junk and write a SKILL.md that measurably improves your agent.
· Travis Rodgers · AITurn an Old MacBook Pro Into a 24/7 AI Agent Server
Got a spare or broken-screen MacBook Pro? Here is how I turned mine into an always-on, closed-lid homelab server for running self-hosted AI agents like OpenClaw and Hermes 24/7.