agentic-karpathy

Community

Surgical coding discipline for safer AI.

Authortmdgusya
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Prevents common LLM coding mistakes by enforcing surgical changes, reading before editing, strict scope discipline, and explicit success criteria during software development.

Core Features & Use Cases

  • Enforces Hard Gates that must be satisfied before changes (Read before you write, Scope to the request, Verify assumptions, Define success).
  • Provides The Five Rules to guide safe coding, including Make Surgical Changes and Read The Existing Code, to minimize unnecessary edits.
  • Suitable for use during feature implementation, refactoring, or code reviews to ensure changes are minimal, well-justified, and verifiable.

Quick Start

Before writing any code, read the Karpathy Guidelines and apply the four hard gates and the five rules to ensure surgical, verifiable edits.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agentic-karpathy
Download link: https://github.com/tmdgusya/roach-pi/archive/main.zip#agentic-karpathy

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.