hun99999/agent-bootstrap
Process-first bootstrap for Codex and Claude Code with superpowers, role-based subagents, token-efficient workflows, and multilingual setup docs.
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 hun99999/agent-bootstrap/agents ./rig-agent-bootstrap/agents $ npx degit hun99999/agent-bootstrap/skills ./rig-agent-bootstrap/skills
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 hun99999/agent-bootstrap/plugins/frontend-design-pack/skills/frontend-design .claude/skills/frontend-design $ npx degit hun99999/agent-bootstrap/skills/chatgpt-collaboration-harness .claude/skills/chatgpt-collaboration-harness $ npx degit hun99999/agent-bootstrap/skills/execute-plan .claude/skills/execute-plan $ npx degit hun99999/agent-bootstrap/skills/focused-debugging .claude/skills/focused-debugging $ npx degit hun99999/agent-bootstrap/skills/handoff .claude/skills/handoff $ npx degit hun99999/agent-bootstrap/skills/hun-engineering-loop .claude/skills/hun-engineering-loop $ npx degit hun99999/agent-bootstrap/skills/isolated-worktree .claude/skills/isolated-worktree $ npx degit hun99999/agent-bootstrap/skills/karpathy-guidelines .claude/skills/karpathy-guidelines $ npx degit hun99999/agent-bootstrap/skills/review-feedback-triage .claude/skills/review-feedback-triage
$ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/data-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/data-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/eng-lead.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/eng-lead.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/integrations-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/integrations-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/performance-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/platform-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/platform-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/release-manager.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-engineer.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/security-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/skill-author.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/skill-author.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/verifier.md $ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/hun99999/agent-bootstrap/main/agents/worker.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"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(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (9)
frontend-designchatgpt-collaboration-harnessexecute-planfocused-debugginghandoffhun-engineering-loopisolated-worktreekarpathy-guidelinesreview-feedback-triage
Subagents (16)
Similar rigs
tylerjkells/claude-dotfiles
—
Pragmatist 579 tok ·
matheusmlopess/myAgenticSetup
WSL2 Ubuntu bootstrap agent — dotfiles, setup scripts, and Claude Code agent for fresh installs
Orchestrator 7.5k tok ·
joaolozano-lendario/athena-os
A Claude Code Native System for Intelligent Workflow Architecture - Slash Commands for Smarter AI Workflows
Orchestrator 3.7k tok ·
juzser/blacksmith
Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.
Orchestrator 2.6k tok ·