ufukyuksel-dev/SUPER_COMPUTER_AI
Build your own super AI: skills, MCP servers, agent roles and instructions for Claude Code and Codex, installed with one reversible command.
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 ufukyuksel-dev/SUPER_COMPUTER_AI/agents ./rig-super_computer_ai/agents 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/architect.md https://raw.githubusercontent.com/ufukyuksel-dev/SUPER_COMPUTER_AI/main/agents/claude/architect.md $ curl -fsSL --create-dirs -o .claude/agents/dataset-curator.md https://raw.githubusercontent.com/ufukyuksel-dev/SUPER_COMPUTER_AI/main/agents/claude/dataset-curator.md $ curl -fsSL --create-dirs -o .claude/agents/evaluator.md https://raw.githubusercontent.com/ufukyuksel-dev/SUPER_COMPUTER_AI/main/agents/claude/evaluator.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/ufukyuksel-dev/SUPER_COMPUTER_AI/main/agents/claude/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/ufukyuksel-dev/SUPER_COMPUTER_AI/main/agents/claude/researcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Subagents (5)
| architect | Turn approved requirements and evidence into architecture, a plan, acceptance criteria, and an evaluation plan. |
| dataset-curator model: haiku | Curate rights-clean, leakage-safe training datasets — collection, cleaning, dedup, splits, tiered synthetic generation, and quality gates. |
| evaluator | Exercise a deliverable against approved criteria and report evidence, failures, and unverified claims. |
| implementer | Execute an approved architecture and plan using only the specialist skills named for the assigned work. |
| researcher | Gather current, primary-source evidence without making architecture decisions or implementing changes. |
Similar rigs
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok · · Q24
Fili999/ai-hub
One hub for your AI coding agents, skills and workflows: write them once, install them into Claude Code, Codex, Antigravity CLI and local models. Free, open source, runs on your computer.
Minimalist 903 tok · · Q8
yuroka-studio/nightshift-agents
Scheduled Claude Code agents that take one task from a backlog, open a PR with real test evidence, and never merge or deploy on their own.
Fort Knox 1.0k tok · · Q61
studioKjm/dre
The business/domain-analysis counterpart to REA — business model, pricing, financials, and marketing evidence for AI agents. BYOK, free, MCP server.
Fort Knox 2.5k tok · · Q20