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.
curl -O https://raw.githubusercontent.com/KbWen/agent-virtual-office/main/.agents/skills/karpathy-principles/SKILL.mdgit clone --depth 1 https://github.com/KbWen/agent-virtual-officeWrote 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.
[](https://agentmods.dev/skills/kbwen/agent-virtual-office/karpathy-principles)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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"
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.
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.
- 9d ago First seen · 143 lines · 34 tokens per session scan A d599b962a01c
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.
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…
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.
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.
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.
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.
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…