dentaco/claude-starter
Alex Znamenskiy's sanitised Claude Code config: settings.json, CLAUDE.md template, typecheck + deploy-watcher hooks, status line, three reviewer agents, safe installer. Cloned in the Build & Ship with AI course (dentaco.ae).
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit dentaco/claude-starter/agents ./rig-claude-starter/agents $ npx degit dentaco/claude-starter/hooks ./rig-claude-starter/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/design-reviewer.md https://raw.githubusercontent.com/dentaco/claude-starter/main/agents/design-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-tester.md https://raw.githubusercontent.com/dentaco/claude-starter/main/agents/qa-tester.md $ curl -fsSL --create-dirs -o .claude/agents/ux-reviewer.md https://raw.githubusercontent.com/dentaco/claude-starter/main/agents/ux-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (3)
| design-reviewer model: sonnet | Judges a live site against a written design bar and flags anything drifting toward a generic template. Use for design reviews; edit the BAR section below to make it your taste. |
| qa-tester model: sonnet | Tests a live website end to end in the real browser and reports what broke. Use after any deploy, or when asked to "test the live site". |
| ux-reviewer model: sonnet | Walks a live site as a first-time user and scores clarity, friction and copy. Use when asked for a UX review or before showing a product to real users. |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write | if [ -f tsconfig.json ]; then npx tsc --noEmit; fi |
| PostToolUse | Bash|mcp__plugin_vercel_vercel__deploy_to_vercel | $HOME/.claude/hooks/post-deploy-ship.sh |
Plugins (2)
frontend-design@claude-plugins-officialvercel@claude-plugins-official
Similar rigs
Iski08/dotclaude
Multi-agent config for Claude Code with specialized agents and templates to speed code review, refactoring, security audits, tech-lead guidance, and UX evaluations across CI pipelines. 🐙
Orchestrator 677 tok ·
Sabeekhann/cc-token-meter
Private, local Claude Code usage intelligence track tokens, estimated cost, cache efficiency, budgets, projects, and live sessions with zero telemetry.
Orchestrator 7.3k tok ·
karkranikhil/sf-ai-toolkit
Make Salesforce DX projects AI-ready with a CLI and VS Code extension that scaffold Cursor/Claude setup, MCP config, diagnostics, and safe deployment guardrails.
Orchestrator 5.3k tok ·
itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
Orchestrator 3.0k tok ·