# claude-playground

A tiny todo CLI that exists to try out [Claude Code](https://docs.claude.com/en/docs/claude-code) features.

```sh
npm test
npm start -- add "try Claude Code"
npm start -- done 1
npm start -- ls
```

## What's set up

| File | Claude Code feature |
| --- | --- |
| `CLAUDE.md` | Project memory, loaded into every session |
| `.claude/settings.json` | Shared permissions + a hook that syntax-checks `.js` files after every edit |
| `.claude/skills/changelog/` | A custom skill — run `/changelog` |
| `.claude/agents/test-writer.md` | A custom subagent — "use the test-writer agent to…" |

## Things to try

- *"There's a bug in how ids are assigned after removing a todo — find it and fix it with a test."*
- *"Use the test-writer agent to cover `src/todo.js`."*
- *"Add a `--json` flag to `ls`."* then `/code-review`
- `/changelog` after a few commits
- Press `shift+tab` to cycle permission modes (e.g. plan mode before a bigger change)
- `/memory` to edit CLAUDE.md, `/agents` and `/hooks` to inspect the setup