Borrowing it
Nothing to install: this file belongs to duolahypercho/andrej-karpathy-skills. 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/duolahypercho/andrej-karpathy-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/duolahypercho/andrej-karpathy-skillsWrote 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/instructions/duolahypercho/andrej-karpathy-skills/agents-md)<a href="https://agentmods.dev/instructions/duolahypercho/andrej-karpathy-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/duolahypercho/andrej-karpathy-skills/agents-md/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/instructions/duolahypercho/andrej-karpathy-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/duolahypercho/andrej-karpathy-skills/agents-md.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 | $0.00312 | $0.00312 |
| Opus 5.5 | $0.00125 | $0.00125 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
andrej-karpathy-skills AGENTS.md 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 2mo 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
AGENTS.md
This repository is a Codex-native plugin package. Treat it as a reusable skill, not as a generic prompt dump.
Source Of Truth
- Plugin manifest:
.codex-plugin/plugin.json - Skill behavior:
skills/andrej-karpathy-skill/SKILL.md - Custom Instructions copy-paste version:
instruction.md - Usage examples:
EXAMPLES.md - Public overview:
README.md
Package Intent
The package teaches Codex the four Karpathy-inspired coding-agent checks:
- think before coding,
- keep implementations simple,
- make surgical changes,
- define the goal and verify it.
Maintenance Rules
- Keep this repository Codex-native.
- Do not add instruction files or plugin metadata for other agent runtimes.
- Keep
SKILL.mdas the behavioral source of truth. - Keep
instruction.mdself-contained so it works withoutAGENTS.md. - Keep examples concrete and code-adjacent, not motivational.
- Keep attribution in
README.md, but do not copy upstream wording wholesale. - Avoid non-ASCII symbols in English docs unless the file already requires them.
Quality Bar
Before publishing a change, confirm:
- The file list still matches the Codex package shape.
- The manifest points to this repository.
- README, AGENTS, and SKILL describe the same behavior.
instruction.mdmatches the same workflow and can be pasted into Custom Instructions.- Examples use clean plain text and do not depend on another runtime.
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.
- 2mo ago First seen · 41 lines · 312 tokens per session scan A 8052e58d7ce1
andrej-karpathy-skills AGENTS.md is an instructions file published in the GitHub repository duolahypercho/andrej-karpathy-skills (284 stars, last pushed 5mo ago), licensed MIT. It adds 312 tokens to every session, about $0.0012 per session on Opus 5.5. 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 2026-08-30.
andrej-karpathy-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| andrej-karpathy-skills AGENTS.mdduolahypercho/andrej-karpathy-skills | Instructions file | 284 | 5mo ago | MIT | A | 312 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |