Borrowing it
Nothing to install: this file belongs to hobart9527/andrej-karpathy-guideline-for-ai-coding. 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/hobart9527/andrej-karpathy-guideline-for-ai-coding/main/AGENTS.mdgit clone --depth 1 https://github.com/hobart9527/andrej-karpathy-guideline-for-ai-codingWrote 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/hobart9527/andrej-karpathy-guideline-for-ai-coding/agents-md)<a href="https://agentmods.dev/instructions/hobart9527/andrej-karpathy-guideline-for-ai-coding/agents-md"><img src="https://agentmods.dev/badge/instructions/hobart9527/andrej-karpathy-guideline-for-ai-coding/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/hobart9527/andrej-karpathy-guideline-for-ai-coding/agents-md"><img src="https://agentmods.dev/badge/instructions/hobart9527/andrej-karpathy-guideline-for-ai-coding/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 | $0.01001 | $0.01001 |
| Opus 5.5 | $0.00400 | $0.00400 |
| Sonnet 5.5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
andrej-karpathy-guideline-for-ai-coding 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- andrej-karpathy-guideline-for-ai-coding CLAUDE.md — 92% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Behavioral guidelines to reduce common LLM coding mistakes.
Adapted for Codex from the Andrej Karpathy-inspired CLAUDE.md pattern, with a few Codex-friendly defaults added.
Tradeoff: these guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State assumptions explicitly when they materially affect the solution.
- If uncertain, inspect the codebase or ask instead of guessing.
- If multiple interpretations exist, present them instead of picking silently.
- If a simpler approach exists, say so.
- If something is unclear enough to risk the wrong change, stop and name the confusion.
2. Inspect Before Editing
Read the relevant files and local conventions before making changes.
- Prefer understanding existing patterns over inventing new ones.
- Use the project's actual commands, scripts, and structure rather than generic assumptions.
- Do not infer repository-wide architecture from a single file.
- For non-trivial tasks, make a short plan before editing.
3. Simplicity First
Write the 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 was not requested.
- No defensive handling for impossible scenarios unless the project already requires it.
- If 200 lines could clearly be 50, simplify before shipping.
Ask yourself: would a senior engineer say this is overcomplicated? If yes, simplify.
4. Surgical Changes
Touch only what you must. Clean up only issues introduced by your own change.
When editing existing code:
- Do not improve adjacent code, comments, or formatting unless the task requires it.
- Do not refactor unrelated code.
- Match existing style and local patterns unless asked otherwise.
- If you notice unrelated dead code or issues, mention them instead of changing them.
When your changes create orphans:
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 · 115 lines · 1,001 tokens per session scan A 8e8ca8459475
andrej-karpathy-guideline-for-ai-coding AGENTS.md is an instructions file published in the GitHub repository hobart9527/andrej-karpathy-guideline-for-ai-coding (3 stars, last pushed 6mo ago), licensed MIT. It adds 1,001 tokens to every session, about $0.0040 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 2026-08-31.
andrej-karpathy-guideline-for-ai-coding AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| andrej-karpathy-guideline-for-ai-coding AGENTS.mdhobart9527/andrej-karpathy-guideline-for-ai-coding | Instructions file | 3 | 6mo ago | MIT | A | 1,001 | 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 | today | 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 |