The claude desktop app can drive the real chrome, so it’s less likely to get blocked

Full claude.md is here: https://github.com/EspoTek/.claude/blob/master/CLAUDE.md

The skills I have installed are:

```

    on         frontend-design:frontend-design · plugin · ~90 tok · locked by plugin
     on         agents-sdk · user · ~150 tok
     on         cloudflare · user · ~130 tok
     on         cloudflare-email-service · user · ~180 tok
     on         durable-objects · user · ~130 tok
     on         find-docs · user · ~300 tok
     on         find-skills · user · ~110 tok
     on         sandbox-sdk · user · ~120 tok
     on         stage-chapters · user · ~40 tok
     on         web-perf · user · ~150 tok
     on         workers-best-practices · user · ~130 tok
     on         wrangler · user · ~120 tok

The plugins I have are:

```

    cc-caffeine Plugin · samber ·  enabled
    frontend-design Plugin · claude-plugins-official ·  enabled
    ty Plugin · claude-code-lsps ·  enabled
    vscode-langservers Plugin · claude-code-lsps ·  enabled
    vtsls Plugin · claude-code-lsps ·  enabled

There's also an MCP for Context7.

But yeah, this is more or less vanilla Claude Code - at least, nothing related to Android or adb there.

It's that good now. A few days ago I asked it to SSH into my Ubuntu box and investigate a hang. It didn't solve the problem fully autonomously like this time but did tell me a whole lot things it wasn't, and hinted at a faulty driver. We went back and forth a bit, it set up a watchdog and taught me how to update the kernel without updating Ubuntu itself, and the server has been rock solid for the past 3-4 days now.

Also, if you're curious, full log for the Kodi issue:

https://github.com/user-attachments/files/28659304/2026-06-0...

I did prompt it a little bit more today in order to get something more production-ready (the original solution kept regenerating the cache on boot, rather than fixing it permanently), but you can see the whole original autonomously-generated solution in the logs. It's insane, seriously.

Claude Code (or Codex, or OpenCode, or Pi, or Amp — whatever) can do this out of the box without any skills or special tools. The most important thing for making results like this easier to achieve (in any harness) is using the best current models. Right now that's Opus 4.8 and GPT-5.5.

LinkedIn in particular is quite aggressively blocking any automated attempts to read or navigate through it.

I post quite a lot there and wanted to have a copy of my posts on my blog[0] to preserve them. For a few months I was able to use a headless browser + claude code, then LI wised up and started logging it out, so I had to use a regular Chrome, log in manually and then tell the LLM to take over and slowly go through my feed.

If you're accessing sites which are not actively blocking bots, or - gasp - have an API, it's much better.

[0] example: https://blog.senko.net/may-quick-takes

To expand on another answer, it’s all about the harness. Different harnesses (Claude Code or Cowork, Hermes, OpenCode, Pi, etc.) offer different default tools, system prompts, and ultimately approaches. (IME the corporate CoPilot app is terrible - basically a chat interface.)

I’m currently using Hermes for local LLMs - seems pretty good so far.