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/bonigarcia/context-engineeringWrote 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/bonigarcia/context-engineering/karpathy-guidelines)<a href="https://agentmods.dev/rules/bonigarcia/context-engineering/karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/bonigarcia/context-engineering/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/bonigarcia/context-engineering/karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/bonigarcia/context-engineering/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 | $0.00407 | $0.00407 |
| Opus 5.5 | $0.00163 | $0.00163 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
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 1mo 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-Inspired Coding Guidelines
These guidelines are inspired by Andrej Karpathy's observations on LLM coding pitfalls (e.g., silent assumptions, over-engineering, unintended side effects, and lack of verification) and the open-source andrej-karpathy-skills project.
1. Think Before Coding
- No Silent Assumptions: Never guess requirements. If a task or specification is ambiguous, ask for clarification.
- Surface Tradeoffs: If there are multiple ways to implement something, list the options and trade-offs before proceeding.
- Push Back: If a simpler design is possible or if requested logic contradicts existing standards, suggest alternatives.
2. Simplicity First
- Minimal Code: Implement the absolute minimum code required to solve the request. Avoid speculative features or abstractions.
- Senior Engineer Test: Write code that passes the "Senior Engineer Test" (clean, readable, and free of over-engineering).
- YAGNI (You Aren't Gonna Need It): Do not add hooks, config parameters, or flexibility options unless explicitly requested.
3. Surgical Changes
- Local Edits Only: Modify only the files and lines necessary to fulfill the request.
- Do Not "Clean Up" Unrelated Code: Avoid formatting, refactoring, or updating adjacent code/comments unless explicitly asked.
- Prune Unused Code: Remove only imports, functions, or variables that your specific changes made obsolete.
4. Goal-Driven Execution
- Tests First: Write or locate the tests that verify the requested behavior before implementing the logic.
- Verifiable Success Criteria: Define exactly how you will verify success (e.g., specific test commands, log outputs).
- Verify Execution: Always run tests to verify your implementation before declaring the task complete.
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.
- 1mo ago First seen · 29 lines · 407 tokens per session scan A 60115ee2710f
karpathy-guidelines is a cursor rule published in the GitHub repository bonigarcia/context-engineering (168 stars, last pushed yesterday), licensed Apache-2.0. It adds 407 tokens to every session, about $0.0016 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.
Other cursor rules, from other repositories
aria-audit
ARIA audit skills — /audit dispatcher plus /audit-knowledge, /audit-config, /audit-style, /audit-usage. Use when user says 'audit knowledge', 'audit config', 'audit style', 'audit usage', 'review setup', or runs the slash commands.
aria-context
ARIA context surfacing — /context and /rules. Use whenever the user asks to load knowledge by topic, references a tag, or asks 'what do we know about X' or 'look up rule N'. Also fires the implicit task-start tag match described in AGENTS.md.
aria-rule-22
Rule 22 — change decision framework. Apply BEFORE every Edit/Write: emit a [Rule 22] block (Low Impact or High Impact 7-step) ABOVE the tool call in the same turn, then run scripts/aria/record-edit-intent.sh to log intent. Verify scope AFTER each edit.
aria-core
ARIA core — five-phase knowledge lifecycle (capture → govern → promote → apply → refresh), knowledge taxonomy, ideas backlog routing, project tier. Consulted whenever ARIA behavior is in question.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.