ed197eeeb14bf306c5bd78b1bbdfa2ce4e9f448f
- Titles and bodies go through --rawfile files, never inline shell quotes - pipefail + curl -f + jq -e so a failed call can't look successful - Fix rounds merge latest main and skip re-opening the PR - Check the branch isn't main before pushing; never bypass the hooks - Review at a pinned level; only correctness findings checked against the code block approval Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
claude-playground
A tiny todo CLI that exists to try out Claude Code features.
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
--jsonflag tols." then/code-review /changelogafter a few commits- Press
shift+tabto cycle permission modes (e.g. plan mode before a bigger change) /memoryto edit CLAUDE.md,/agentsand/hooksto inspect the setup
Languages
JavaScript
91.4%
Shell
8.6%