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.
npx agentmods add rules/bonigarcia/context-engineering/karpathy-guidelinesgit clone --depth 1 https://github.com/bonigarcia/context-engineeringWhat 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 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 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 2d 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.
- 2d 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 (132 stars, last pushed 3d ago), licensed Apache-2.0. It adds 407 tokens to every session, about $0.0020 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 cursor rules, from other repositories
cursorrules
Project: AI Platform Engineering Type: Python Backend for AI Agents & Multi-Agent System Language: Python 3.11+ Framework: LangGraph, LangChain, A2A Protocol Package Manager: uv Testing: pytest.
specify-rules
Project Development Guidelines.
safe-git-worktree
Protect the user's live working tree during branch/PR work; verify a current base, preserve uncommitted edits, and isolate risky work in a worktree.
docker-compose-first-install
Use the Docker Compose first-install skill when Compose, env examples, release images, Keycloak/OpenFGA/RAG defaults, or first-launch UX changes.
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-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.