agentrigs
+ submit rig
~ / rigs / a-tokyo / aiworkspace

a-tokyo/aiworkspace

🧑‍💻 Set up and manage AI agent skills and configs for Cursor, Claude Code, Codex and more across multi-repo workspaces.

↗ GitHub ★ 21 Apache-2.0 updated 2mo ago project Claude CodeCodexCursorCopilot
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.3k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http context7 https://mcp.context7.com/mcp/oauth
$ npx degit a-tokyo/aiworkspace/root-config/.claude ./rig-aiworkspace  # 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.

$ claude mcp add --transport http context7 https://mcp.context7.com/mcp/oauth
$ npx degit a-tokyo/aiworkspace/.agents/skills/autoresearch .claude/skills/autoresearch
$ npx degit a-tokyo/aiworkspace/.agents/skills/production-grade .claude/skills/production-grade
$ npx degit a-tokyo/aiworkspace/.agents/skills/tribunal .claude/skills/tribunal
$ npx degit a-tokyo/aiworkspace/root-config/.agents/skills/scaffold-skill .claude/skills/scaffold-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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
Context7 remote · remote 1.2k

Skills (4)

autoresearchproduction-gradetribunalscaffold-skill

Cursor rules (1)

workspace · always

Permissions

deny (0)
—
ask (0)
—
allow (5)
Bash(npm run *)
Bash(npx *)
Bash(git *)
Bash(gh *)
mcp__context7__*

Similar rigs

uditgoenka/autoresearch
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
★ 5,821 project Claude CodeCodex 1 skills 2mo ago
Pragmatist 2.6k tok ·
drivelineresearch/autoresearch-claude-code
Autonomous experiment loop skill for Claude Code — port of pi-autoresearch
★ 346 project Claude CodeCodex 1 skills 1mo ago
Minimalist 569 tok ·
edbizarro/dotfiles
:skull: dotfiles! managed by GNU stow
★ 102 setup Claude CodeCodexGemini CLI 1 mcp 2mo ago
Pragmatist 2.9k tok ·
jesseoue/universal-agent-config
One source of truth for AI coding agent configuration and model routing. Generates native configs for OpenCode, omp, Claude Code, Codex, Cursor, Aider, and Goose with OpenRouter, Cloudflare, Vercel, LiteLLM, and Portkey routing.
★ 3 setup Claude CodeCodex 1 mcp 1mo ago
Minimalist 2.2k tok ·
copied ✓