simplercode
Make your Python shorter and simpler, with every refactor checked against the original.
Your AI agent (Claude Code or Codex) writes the refactors. simplercode checks every one against your original and
only offers you a version that passed every check and is simpler. Nothing changes in your code unless you choose
Apply.
Two ways to use it
- Auto mode: turn on Simplest first, while your agent writes in the goatedcode sidebar, and your agent
writes the simplest correct version first, as it codes.
- Refactor: click Simplify above any function to clean up code that already exists, one function at a time,
with the full check below.
How a refactor works
- Pick a function. Click Simplify above any Python function.
- Choose the goal: fewer lines of code, or fewer decision paths (lower complexity).
- Your agent refactors it in its own workspace. Your files aren't touched while it works.
- simplercode checks every refactor independently: your real inputs, generated edge cases, side effects (files,
output, arguments changed) and your project's own tests. A refactor that changes anything, or becomes much slower,
is rejected.
- You decide. You see the before and after, with the diff, and one question: apply it or not.
The goatedcode fuzzing method
Every refactor is checked by the goatedcode engine, not by the agent that wrote it:
- Your real inputs: the calls your program actually makes, recorded and replayed against the original and the
refactor.
- Generated edge cases: fuzzed inputs (empty, zero, negative, huge, unusual values), plus a search for any input
where the two disagree.
- Side effects: files written, output printed and arguments changed, compared as well as return values.
- Your own tests: the project's tests that call the code are run again.
The tests are saved locally. Every check becomes an ordinary test script on your machine, in goatedcode's own
folder, or in your repo's tests/goated/ if you choose. You can read it, run it and add your own cases, and
goatedcode includes them in every later check.
The reports are saved locally too. Every run's report (what was checked, what changed and the measurements) is
kept on your machine, in goatedcode's own folder outside your repo, so you can open it again or attach it to a pull
request.
Your code stays yours
Everything runs on your machine. simplercode never uploads your code.
Part of goatedcode
simplercode is one of the goatedcode tools, built on the same engine as fastercode, with
more coming.
Installing it also installs the goatedcode core. Free in VS Code while we launch. See simplercode.ai and
goatedcode.com.