robotostudio/turbo-start-web-agent
Agent-native marketing site template — git-based MDX content, a 19-Block system, and a generated harness run live on Claude Code, Codex and v0.
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 robotostudio/turbo-start-web-agent/.claude ./rig-turbo-start-web-agent # inspect, then merge into .claude/ 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.
$ npx degit robotostudio/turbo-start-web-agent/.agents/skills/compose-page .claude/skills/compose-page $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/design-a-block .claude/skills/design-a-block $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/find-skills .claude/skills/find-skills $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/humanizer .claude/skills/humanizer $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/no-em-dash-copy .claude/skills/no-em-dash-copy $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/sync-changes .claude/skills/sync-changes $ npx degit robotostudio/turbo-start-web-agent/.agents/skills/write-a-skill .claude/skills/write-a-skill
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 *)"
]
}
} Skills (7)
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup | if [ "$CLAUDE_CODE_REMOTE" = "true" ]; then sh "$CLAUDE_PROJECT_DIR/scripts/preflight.sh"; fi |
Similar rigs
weimeng23/claude-code-dotfiles
Personal Claude Code dotfiles for global instructions, settings, hooks, agents, and reusable setup scripts.
Pragmatist 984 tok ·
Leon-Drq/openagentskill
The skill layer for AI agents: npm for AI Agent Skills.
Minimalist 610 tok ·
Aboudjem/humanizer-skill
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
Minimalist 1.7k tok ·
GrassHeadd/dotfiles
Personal dotfiles: fish, ghostty, nvim, tmux, aerospace, Claude Code + Codex configs
Pragmatist 5.0k tok ·