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.
git clone --depth 1 https://github.com/Vincent-A-Yang/karpathy-skills-anycodingWrote 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/rules/vincent-a-yang/karpathy-skills-anycoding/karpathy-guidelines)<a href="https://agentmods.dev/rules/vincent-a-yang/karpathy-skills-anycoding/karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/vincent-a-yang/karpathy-skills-anycoding/karpathy-guidelines/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/rules/vincent-a-yang/karpathy-skills-anycoding/karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/vincent-a-yang/karpathy-skills-anycoding/karpathy-guidelines.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 | $0.00212 | $0.00212 |
| Opus 5 | $0.00106 | $0.00106 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
karpathy-guidelines 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.
What it actually says
Karpathy behavioral guidelines
1. Think Before Coding
Do not assume. Do not hide confusion. Surface tradeoffs.
- State assumptions explicitly.
- Ask when ambiguity materially affects implementation.
- Present simpler alternatives when they exist.
2. Simplicity First
Write the minimum code that correctly solves the problem.
- No extra features.
- No speculative abstractions.
- No unnecessary configurability.
3. Surgical Changes
Touch only what you must.
- Do not refactor unrelated code.
- Do not rewrite nearby formatting or comments without cause.
- Match the surrounding style.
4. Goal-Driven Execution
Define success criteria and verify them.
- Reproduce bugs before fixing them when feasible.
- Prefer tests or direct evidence.
- Use a short step-and-verify plan for multi-step work.
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 · 39 lines · 212 tokens per session scan A 46b544a9cf8d
karpathy-guidelines is a cursor rule published in the GitHub repository Vincent-A-Yang/karpathy-skills-anycoding (3 stars, last pushed 4mo ago), licensed MIT. It adds 212 tokens to every session, about $0.0011 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.
Other cursor rules, from other repositories
engine-internals
Coding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior.
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
qmd-search
Prefer QMD over grep/ripgrep for searching vault content.
skill-conventions
Project conventions for creating and editing Obsidian vault skills.
skill-registry
When a skill is created, renamed, or deleted, update the skill registry.
migration
A set of rules for writing database migration scripts, which are files that change a database's structure over time. It covers MySQL 8 tables, columns, filenames, locations, and required fields.