xeeva/Genesis
Bootstrap fully-equipped Claude Code projects in under two minutes. Agents, skills, hooks, memory, MCP configs — all scaffolded from a single conversation.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit xeeva/Genesis/.claude ./rig-genesis # 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 xeeva/Genesis/.claude/skills/genesis .claude/skills/genesis $ npx degit xeeva/Genesis/.claude/skills/registry .claude/skills/registry $ npx degit xeeva/Genesis/.claude/skills/update .claude/skills/update $ npx degit xeeva/Genesis/.claude/skills/validate .claude/skills/validate
$ curl -fsSL --create-dirs -o .claude/agents/claude-infra-writer.md https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/agents/claude-infra-writer.md $ curl -fsSL --create-dirs -o .claude/agents/finaliser.md https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/agents/finaliser.md $ curl -fsSL --create-dirs -o .claude/agents/interviewer.md https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/agents/interviewer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/scaffold-writer.md https://raw.githubusercontent.com/xeeva/Genesis/main/.claude/agents/scaffold-writer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (4)
Subagents (5)
| claude-infra-writer | — |
| finaliser | — |
| interviewer | — |
| planner | — |
| scaffold-writer | — |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| Stop | * | Check the last assistant message. If it contains a project generation summary (phrases like 'Project created:', 'scaffold complete', 'Next steps:', or a project path), respond with {"ok": false, "reason": "Remind the user to cd into the pro |
Permissions
deny (0)
—
ask (0)
—
allow (12)
Read
Edit
Write
Glob
Grep
Bash(mkdir:*)
Bash(git:*)
Bash(ls:*)
Bash(cp:*)
Bash(chmod:*)
Bash(test:*)
Bash(cat:*)
Similar rigs
stavrespasov/claude-code-os-lite
A free, installable starter setup for Claude Code: 10 workflow commands, 2 agents, and the hook that ends --no-verify commits. MIT.
Pragmatist 101 tok ·
PranavMishra17/Claude-setup
Reusable Claude Code template for structured, agent-driven development. Includes planning agents, feature executors, workflow commands, and safety hooks ready to drop into any project.
Automator 1.3k tok ·
CreatmanCEO/claude-code-antiregression-setup
Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.
Pragmatist 96 tok ·
studiowebux/cerveau.dev
Multi-brain protocol for Claude Code — one shared protocol, many projects, zero duplication. MDPlanner-driven workflow with selective rules, hooks, and agents per project.
Minimalist 28 tok ·