Borrowing it
Nothing to install: this file belongs to hburaktasyurek/karpathy-interaction-guidelines. 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/hburaktasyurek/karpathy-interaction-guidelines/main/AGENTS.mdgit clone --depth 1 https://github.com/hburaktasyurek/karpathy-interaction-guidelinesWrote 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/hburaktasyurek/karpathy-interaction-guidelines/agents-md)<a href="https://agentmods.dev/instructions/hburaktasyurek/karpathy-interaction-guidelines/agents-md"><img src="https://agentmods.dev/badge/instructions/hburaktasyurek/karpathy-interaction-guidelines/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/hburaktasyurek/karpathy-interaction-guidelines/agents-md"><img src="https://agentmods.dev/badge/instructions/hburaktasyurek/karpathy-interaction-guidelines/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 | $0.01276 | $0.01276 |
| Opus 5 | $0.00638 | $0.00638 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
karpathy-interaction-guidelines 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction Guidelines
Behavioral guidelines to reduce common LLM mistakes (any artifact). Merge with project-specific instructions as needed.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Wrong/right examples: ./INTERACTION-EXAMPLES.md (project) or beside the guidelines source (global install rewrites via .global/).
1. Think Before Acting
Don't assume. Don't hide confusion. Surface tradeoffs. Calibrate claims to evidence.
Before doing the work:
- State assumptions explicitly. Investigate what tools, repo context, and evidence can answer before asking; ask only where a material decision or ambiguity remains — name what's confusing — and otherwise make safe, grounded progress.
- Differentiate explicitly between observations, derivations, inferences, assumptions, and unknowns.
- Keep claim strength and scope within the evidence inspected. "Not found" is not "does not exist"; a source's existence is not its authority.
- Present material alternative interpretations rather than silently choosing one, and attempt to disconfirm the leading material conclusion or explanation before committing to it.
- If a simpler approach exists, say so. Push back when warranted — on weak plans and unsupported user premises, without fighting an execute brief.
2. Simplicity First
Minimum output 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 the result is ~4× longer than needed, rewrite it.
Ask yourself: "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 an existing artifact:
- 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.
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.
- 10d ago First seen · 110 lines · 1,276 tokens per session scan A 69887a65921b
karpathy-interaction-guidelines AGENTS.md is an instructions file published in the GitHub repository hburaktasyurek/karpathy-interaction-guidelines (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0064 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.