Claude can write complete Datasette plugins now

8th October 2025

This isn’t necessarily surprising, but it’s worth noting anyway. Claude Sonnet 4.5 is capable of building a full Datasette plugin now.

I’ve seen models complete aspects of this in the past, but today is the first time I’ve shipped a new plugin where every line of code and test was written by Claude, with minimal prompting from myself.

The plugin is called datasette-os-info. It’s a simple debugging tool—all it does is add a /-/os JSON page which dumps out as much information as it can about the OS it’s running on. Here’s a live demo on my TIL website.

I built it to help experiment with changing the Docker base container that Datasette uses to publish images to one that uses Python 3.14.

Here’s the full set of commands I used to create the plugin. I started with my datasette-plugin cookiecutter template:

This created a datasette-os-info directory with the initial pyproject.toml and tests/ and datasette_os_info/__init__.py files. Here’s an example of that starter template.

I created a uv virtual environment for it, installed the initial test dependencies and ran pytest to check that worked:

Then I fired up Claude Code in that directory in YOLO mode:

(I actually used my claude-yolo shortcut which runs the above.)

Then, in Claude, I told it how to run the tests:

Run uv run pytest

When that worked, I told it to build the plugin:

This is a Datasette plugin which should add a new page /-/os which returns pretty-printed JSON about the current operating system - implement it. I want to pick up as many details as possible across as many OS as possible, including if possible figuring out the base image if it is in a docker container - otherwise the Debian OS release name and suchlike would be good

... and that was it! Claude implemented the plugin using Datasette’s register_routes() plugin hook to add the /-/os page,and then without me prompting it to do so built this basic test as well.

It ran the new test, spotted a bug (it had guessed a non-existent Response(..., default_repr=) parameter), fixed the bug and declared itself done.

I built myself a wheel:

Then uploaded that to an S3 bucket and deployed it to test it out using datasette publish ... --install URL-to-wheel. It did exactly what I had hoped—here’s what that /-/os page looked like:

I dread to think how long it would have taken me to figure out all of those different useful OS details!

To finish up, I had Claude fill out the README via a couple of extra prompts:

Add usage instructions to the README (about the /-/os page)

Then had a brief conversation about how safe the output was:

Is there anything potentially sensitive in that output?

Claude said:

Yes, there are several potentially sensitive items in the output:

Most sensitive:

• hostname—Could reveal internal naming schemes or organization details
• Environment variables:
  • HOME—Reveals user’s home directory path
  • USER—Reveals the username
  • PATH—Reveals filesystem structure and software installation locations
  • VIRTUAL_ENV—Could reveal project paths and directory structure
• python_executable—Reveals filesystem paths and user directories

Moderately sensitive:

• CPU count and memory info—Could reveal infrastructure capacity
• Kernel version details—Could potentially be used to identify specific vulnerabilities

Considerations:

1. This endpoint is accessible without authentication by default (at /-/os)
2. If you’re running Datasette on a public server, this information would be visible to anyone
3. The information could help attackers understand your infrastructure setup

Suggestions:

You might want to:

1. Add authentication requirements to this endpoint
2. Make certain fields optional/configurable
3. Add a warning in the README that this exposes system information
4. Consider filtering out or redacting sensitive paths (replace usernames with ***, etc.)

Would you like me to add any of these protections to the plugin?

In this case I’m fine with the current behavior provided people understand the risks, so I told it:

Add the warning to the README

And then (because the warning it added was quite long):

Drop the bit about configuring the permission system, just have a short warning telling people to review what it exposes

And requested an extra README note:

Add a note that you can also see the output by running: datasette --get /-/os

Three last prompts:

• Add uv.lock to gitignore
• Drop Python 3.9 and add Python 3.14 - to the GitHub workflows, also min version in pyproject.toml
• Bump to setup-python@v6

... and that was the project finished. I pushed it to GitHub, configured Trusted Publishing for it on PyPI and posted the 0.1 release, which ran this GitHub Actions publish.yml and deployed that release to datasette-os-info on PyPI.

Now that it’s live you can try it out without even installing Datasette using a uv one-liner like this:

That’s using the --get PATH CLI option to show what that path in the Datasette instance would return, as described in the Datasette documentation.

I’ve shared my full Claude Code transcript in a Gist.

A year ago I’d have been very impressed by this. Today I wasn’t even particularly surprised that this worked—the coding agent pattern implemented by Claude Code is spectacularly effective when you combine it with pre-existing templates, and Datasette has been aroung for long enough now that plenty of examples of plugins have made it into the training data for the leading models.