agent-virtual-office: Skill for Codex

.agents/skills/karpathy-principles/SKILL.md

karpathy-principles is a skill for Codex from KbWen/agent-virtual-office. It costs 34 tokens per session (1,408 once invoked), scanned A, a copy of karpathy-principles, MIT.

A set of coding guidelines based on observations about common mistakes made by AI coding tools.

In plain words
What is it for?
It guides planning, implementation, and review by encouraging explicit assumptions, simple solutions, focused changes, and checks against the original request.
Why use it?
It helps prevent unnecessary complexity, hidden assumptions, broad edits, and work that does not directly serve the requested goal.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is KbWen/agent-virtual-office's own configuration. It tells Codex how to work on agent-virtual-office itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-virtual-office configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KbWen/agent-virtual-office. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KbWen/agent-virtual-office/main/.agents/skills/karpathy-principles/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/KbWen/agent-virtual-office

Made for: Codex.

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/kbwen/agent-virtual-office/karpathy-principles/github.svg)](https://agentmods.dev/skills/kbwen/agent-virtual-office/karpathy-principles)
Your own site
<a href="https://agentmods.dev/skills/kbwen/agent-virtual-office/karpathy-principles"><img src="https://agentmods.dev/badge/skills/kbwen/agent-virtual-office/karpathy-principles/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for karpathy-principles

Your own site · 80×15
<a href="https://agentmods.dev/skills/kbwen/agent-virtual-office/karpathy-principles"><img src="https://agentmods.dev/badge/skills/kbwen/agent-virtual-office/karpathy-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00034 $0.01408
Opus 5 $0.00017 $0.00704
Sonnet 5 $0.00007 $0.00282
Haiku 4.5 $0.00003 $0.00141

Measured 9d ago against content hash d599b962a01c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

Origin

This is a copy

100% identical to karpathy-principles — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/karpathy-principles/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 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 LLM coding pitfalls.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

When to Apply

  • Classification: quick-win, feature, architecture-change, hotfix
  • Phase: /plan (assumption surfacing), /implement (simplicity + surgical), /review (scope audit)
  • Trigger: All non-trivial coding tasks — this is a behavioral baseline, not a domain skill

1. Think Before Coding

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

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them — don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. 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 you write 200 lines and it could be 50, rewrite it.

Self-check: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

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

When editing existing code:

  • 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.

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

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "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 · 143 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 143 lines · 34 tokens per session scan A d599b962a01c

Subscribe to this mod's changes

karpathy-principles is a skill published in the GitHub repository KbWen/agent-virtual-office (18 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,408 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to karpathy-principles, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

devtools-vite-plugin

Configure @tanstack/devtools-vite for source inspection (data-tsd-source, inspectHotkey, ignore patterns), console piping (client-to-server, server-to-client, levels), enhanced logging, server event bus (port, host, HTTPS), production stripping (removeDevtoolsOnBuild), editor integration (launch-editor, custom…

TanStack/devtools · 93 tokens

devtools-marketplace

Publish plugin to npm and submit to TanStack Devtools Marketplace. PluginMetadata registry format, plugin-registry.ts, pluginImport (importName, type), requires (packageName, minVersion), framework tagging, multi-framework submissions, featured plugins.

TanStack/devtools · 54 tokens

devtools-production

Handle devtools in production vs development. removeDevtoolsOnBuild, devDependency vs regular dependency, conditional imports, NoOp plugin variants for tree-shaking, non-Vite production exclusion patterns.

TanStack/devtools · 43 tokens

devtools-bidirectional

Two-way event patterns between devtools panel and application. App-to-devtools observation, devtools-to-app commands, time-travel debugging with snapshots and revert. structuredClone for snapshot safety, distinct event suffixes for observation vs commands, serializable payloads only.

TanStack/devtools · 59 tokens

devtools-app-setup

Install TanStack Devtools, pick framework adapter (React/Vue/Solid/Preact), register plugins via plugins prop, configure shell (position, hotkeys, theme, hideUntilHover, requireUrlFlag, eventBusConfig). TanStackDevtools component, defaultOpen, localStorage persistence.

TanStack/devtools · 66 tokens

devtools-plugin-panel

Build devtools panel components that display emitted event data. Listen via EventClient.on(), handle theme (light/dark), use @tanstack/devtools-ui components. Plugin registration (name, render, id, defaultOpen), lifecycle (mount, activate, destroy), max 3 active plugins. Two paths: Solid.js core with devtools-ui for…

TanStack/devtools · 84 tokens