agentrigs
+ submit rig
~ / rigs / uditgoenka / autoresearch

uditgoenka/autoresearch

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

↗ GitHub ★ 5,821 mit updated 2mo ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit uditgoenka/autoresearch/.claude ./rig-autoresearch  # 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 uditgoenka/autoresearch/.agents/skills/autoresearch .claude/skills/autoresearch

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 (1)

autoresearch

Slash commands (14)

/autoresearch/autoresearch/debug/autoresearch/evals/autoresearch/fix/autoresearch/improve/autoresearch/learn/autoresearch/plan/autoresearch/predict/autoresearch/probe/autoresearch/reason/autoresearch/regression/autoresearch/scenario/autoresearch/security/autoresearch/ship

Similar rigs

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 ·
a-tokyo/aiworkspace
🧑‍💻 Set up and manage AI agent skills and configs for Cursor, Claude Code, Codex and more across multi-repo workspaces.
★ 21 project Claude CodeCodexCursor 1 mcp 4 skills 2mo ago
Pragmatist 3.3k tok ·
maystudios/maxsimcli
Solve context rot in AI coding. Spec-driven development system for Claude Code, OpenCode, Gemini CLI, and Codex — with parallel subagents, atomic commits, and a live dashboard.
★ 11 project Codex 16 skills 6mo ago
Skill Collector 3.1k tok ·
petertriho/nix-config
Personal nix flakes config
★ 4 setup Claude Code 16 skills 8 hooks today
YOLO Cowboy 1.3k tok ·
copied ✓