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/double-coding-lab/Flow2SpecWrote 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/double-coding-lab/flow2spec/f2s-karpathy-guidelines)<a href="https://agentmods.dev/rules/double-coding-lab/flow2spec/f2s-karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/double-coding-lab/flow2spec/f2s-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/double-coding-lab/flow2spec/f2s-karpathy-guidelines"><img src="https://agentmods.dev/badge/rules/double-coding-lab/flow2spec/f2s-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 | $0.00819 | $0.00819 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
f2s-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 式编码行为准则
与项目内 Flow2Spec /
f2s-*规则并行；若某条与 f2s 强制步骤冲突，以 f2s 与项目约定为准。
用于减少常见「模型写代码」失误的行为约定。
取舍： 这些准则偏向稳妥而非一味求快；对明显琐碎的修改（如单行笔误）可自行把握，不必条条刻板执行。
1. 先想清楚再写代码
不要默认、不要藏困惑、把权衡摆到台面上。
动手实现前：
- 假设要说清楚；不确定就问，不要猜。
- 有多种理解时并列说明，不要悄悄选一种就跑。
- 若有更简单做法，主动提出；该反对时要反对。
- 说不清就停：点名哪里困惑，再向用户要信息。
2. 简单优先
用最少代码解决问题，不做臆测性扩展。
- 不要超出需求加功能。
- 不要为只用一次的代码抽抽象。
- 不要加未被要求的「灵活性」「可配置」。
- 不要为几乎不可能的场景堆错误处理。
- 若写了 200 行其实 50 行就够，重写。
自问：「资深工程师会不会觉得过度设计？」若是，就简化。
3. 手术式修改
只动该动的；只收拾自己弄乱的。
改已有代码时：
- 不要顺手「优化」相邻代码、注释或格式。
- 不要重构没坏的东西。
- 风格对齐现有代码，即使你个人偏好不同。
- 若发现与任务无关的死代码，可以提一嘴，不要擅自删。
若你的改动产生了孤儿引用/变量：
- 删掉因你这次改动而不再使用的 import、变量、函数。
- 不要在用户未要求时删除原本就存在的死代码。
检验标准：每一行改动都能追溯到用户的明确诉求。
4. 目标驱动执行
先定义成功标准，再循环直到可验证地达成。
把任务变成可验证目标，例如：
- 「加校验」→「先写非法入参测试，再改到通过」
- 「修 bug」→「先写能复现的测试，再改到通过」
- 「重构 X」→「前后测试套件均通过」
多步骤任务可写简短计划：
1. [步骤] → 验证：[检查方式]
2. [步骤] → 验证：[检查方式]
3. [步骤] → 验证：[检查方式]
成功标准越具体，越能独立迭代；含糊的「跑通就行」会逼出反复追问。
准则在起作用的信号： diff 里无关改动变少、因过度设计返工变少、澄清问题出现在实现之前而不是做错之后。
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 · 78 lines · 819 tokens per session scan A f9956c1534fa
f2s-karpathy-guidelines is a cursor rule published in the GitHub repository double-coding-lab/Flow2Spec (52 stars, last pushed 6d ago), licensed MIT. It adds 819 tokens to every session, about $0.0033 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
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .