karpathy-principles

karpathy-principles is a skill for Claude Code, Codex from tu11aa/squadrant. It costs 51 tokens per session (812 once invoked), scanned A, original, MIT.

A set of four coding principles based on observations about common AI coding mistakes: think first, keep solutions simple, make focused changes, and review carefully.

In plain words
What is it for?
Use it to guide coding tasks and reviews toward explicit assumptions, minimal changes, and simpler solutions.
Why use it?
It helps prevent guessed requirements, unnecessary complexity, unrelated edits, and vague implementation work.

Skill for Claude CodeCodex

Part of the squadrant plugin — 18 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tu11aa/squadrant/karpathy-principles
Any agent
npx skills add tu11aa/squadrant --skill karpathy-principles
Clone the repo
git clone --depth 1 https://github.com/tu11aa/squadrant

Made for: Claude Code, Codex.

Or install squadrant, the plugin that ships this one along with the rest of its 18 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for karpathy-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/tu11aa/squadrant/karpathy-principles.svg)](https://agentmods.dev/skills/tu11aa/squadrant/karpathy-principles)
Your own site
<a href="https://agentmods.dev/skills/tu11aa/squadrant/karpathy-principles"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/karpathy-principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00812
Opus 5 $0.00026 $0.00406
Sonnet 5 $0.00010 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured 5d ago against content hash 945f366b10bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

karpathy-principles scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/karpathy-principles/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Karpathy Coding Principles

Derived from Andrej Karpathy's observations on how LLMs fail at coding. Ported from forrestchang/andrej-karpathy-skills (MIT).

These four principles apply to every coding task — whether you are a captain reviewing a crew's work or a crew member writing code.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

  • State assumptions explicitly — if uncertain, ask rather than guess
  • Present multiple interpretations when ambiguity exists — don't pick silently
  • Push back when warranted — if a simpler approach exists, say so
  • Stop when confused — name what's unclear and ask

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked
  • No abstractions for single-use code
  • No "flexibility" or "configurability" that wasn't requested
  • No error handling for impossible scenarios
  • If 200 lines could be 50, rewrite

Test: Would a senior engineer call this overcomplicated? If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

  • Don't improve adjacent code, comments, or formatting
  • Don't refactor things that aren't broken
  • Match existing style, even if you'd do it differently
  • If you notice unrelated dead code, mention it — don't delete it

When your changes create orphans:

  • Remove imports/variables/functions that your changes made unused
  • Don't remove pre-existing dead code unless asked

Test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform imperative tasks into verifiable goals:

Instead of... Transform to...
"Add validation" "Write tests for invalid inputs, then make them pass"
"Fix the bug" "Write a test that reproduces it, then make it pass"
"Refactor X" "Ensure tests pass before and after"

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 83 lines · 51 tokens per session scan A 945f366b10bd

Subscribe to this mod's changes

karpathy-principles is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 812 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens