Rodney and Claude Code for Desktop

⋅

I’m a very heavy user of Claude Code on the web, Anthropic’s excellent but poorly named cloud version of Claude Code where everything runs in a container environment managed by them, greatly reducing the risk of anything bad happening to a computer I care about.

I don’t use the web interface at all (hence my dislike of the name) – I access it exclusively through their native iPhone and Mac desktop apps.

Something I particularly appreciate about the desktop app is that it lets you see images that Claude is “viewing” via its Read /path/to/image tool. Here’s what that looks like:

Screenshot of a Claude Code session in Claude Desktop. Claude says: The debug page looks good - all items listed with titles and descriptions. Now let me check the nav menu - Analyzed menu image file - Bash uvx rodney open "http://localhost:8765/" 2>&1 && uvx rodney click "details.nav-menu summary" 2>&1 &% sleep 0.5 && uvx rodney screenshot /tmp/menu.png 2>&1 Output reads: Datasette: test, Clicked, /tmp/menu.png - then it says Read /tmp/menu.png and reveals a screenshot of the Datasette interface with the nav menu open, showing only "Debug" and "Log out" options. Claude continues: The menu now has just "Debug" and “Log out" — much cleaner. Both pages look good. Let me clean up the server and run the remaining tests.

This means you can get a visual preview of what it’s working on while it’s working, without waiting for it to push code to GitHub for you to try out yourself later on.

The prompt I used to trigger the above screenshot was:

Run "uvx rodney --help" and then use Rodney to manually test the new pages and menu - look at screenshots from it and check you think they look OK

I designed Rodney to have –help output that provides everything a coding agent needs to know in order to use the tool.

The Claude iPhone app doesn’t display opened images yet, so I requested it as a feature just now in a thread on Twitter.

Tags: anthropic, claude, ai, claude-code, llms, async-coding-agents, coding-agents, generative-ai, projects, ai-assisted-programming

Liked Liked