New Paid listings are open — 20 founding slots, 3 per category. Book by 30 November. Paid listings are open — 20 founding slots.
HomeToolsCategoriesModel watchFuelGoldInsightsTrendsDailyHow we vetAdvertiseContact
Submit a tool

Claude Code

Anthropic's terminal agent: describe the change, it reads the repo and edits the files itself.

AI CodingPaid★4.6 editor score

What it does

Claude Code runs in your terminal, reads the repository, plans the change, edits files, runs tests and iterates until the tests pass. It works on real codebases rather than snippets, and it asks before doing anything destructive.

It is strongest on refactors, test backfills and well-scoped bug fixes inside a codebase that already has tests. Give it an ambiguous product requirement with no tests and it will produce a confident change you cannot verify.

Standout features

  • Repository-wide reading and editing
  • Runs tests and iterates until they pass
  • Plan-then-approve workflow
  • Works in the terminal and major IDEs

Main job: Delegate a scoped engineering task to an agent that can edit and verify it.

Best for

Coding agentTerminalRefactoring

Refactors, test backfills and bug fixes in repos that already have tests.

Getting started

Point it at one directory, ask for a plan first, then approve step by step. Keep the repo clean and commit before you start so a bad run is one `git reset` away, and let it run the test suite itself rather than describing what it would do.

Watch out for

Watch out: it can run shell commands, so treat it as a junior engineer with your credentials. Never run it against production config or a repo with live secrets, and read the diff before you merge — passing tests are not the same as correct behaviour.