agentrigs
+ submit rig
~ / rigs / multica-ai / andrej-karpathy-skills

multica-ai/andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

↗ GitHub ★ 217k no license updated 6mo ago collection Claude CodeCursor Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~723 tokens
Featherweight · 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 multica-ai/andrej-karpathy-skills/skills ./rig-andrej-karpathy-skills/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 multica-ai/andrej-karpathy-skills/skills/karpathy-guidelines .claude/skills/karpathy-guidelines

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)

karpathy-guidelines

Cursor rules (1)

karpathy-guidelines · always

Similar rigs

swarmclawai/andrej-karpathy-skills
Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.
★ 36 collection Claude CodeCodexCursor 1 skills 5mo ago
Pragmatist 3.1k tok ·
MackDing/andrej-karpathy-skills-zh
Claude Code / Codex / Cursor AI 编程规则：Karpathy 编码准则中文版，减少错误假设、过度工程化和无关改动
★ 1 project Claude CodeCodexCursor 1 skills 5mo ago
Minimalist 614 tok ·
aleconf/claude-code-spec-scaffold
Opinionated scaffolding for spec-driven AI coding — so your sessions leave behind artefacts, not scrollback.
★ 1 project Claude Code 2 skills 2 hooks 4mo ago
Minimalist 1.1k tok ·
0-AI-UG/cate
An infinite zoomable canvas for coding. Editor, terminal, and browser panels in a spatial workspace.
★ 2,167 project Claude CodeCodex 3 skills 9d ago
Minimalist 2.2k tok ·
copied ✓