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/zhu1090093659/growthWrote 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/zhu1090093659/growth/abstraction-uplift)<a href="https://agentmods.dev/rules/zhu1090093659/growth/abstraction-uplift"><img src="https://agentmods.dev/badge/rules/zhu1090093659/growth/abstraction-uplift/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/zhu1090093659/growth/abstraction-uplift"><img src="https://agentmods.dev/badge/rules/zhu1090093659/growth/abstraction-uplift.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 | $0.00172 | $0.03374 |
| Opus 5 | $0.00086 | $0.01687 |
| Sonnet 5 | $0.00034 | $0.00675 |
| Haiku 4.5 | $0.00017 | $0.00337 |
Grade A, and why
abstraction-uplift 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 9d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Abstraction Uplift — 抽象升级
AI 时代代码生成成本趋零,但代码的可理解性、一致性、可演化性会成为新的瓶颈。抽象是管理这三者的核心工具。
本 skill 的使命不是帮用户"重构"——重构是结果。它的使命是帮用户看清楚自己当前抽象的形状,以及看到可能的升级方向。方向对了,重构自己会发生。
核心哲学
好的抽象不是"更多的层",而是**"让相关的东西靠在一起,无关的东西隔开"**(Information hiding / separation of concerns 的本质)。
这意味着抽象升级有两个方向,本 skill 对两者同等看重:
- Lift up(往上抽):看到重复的模式,把它提取成一个概念
- Peel off(往下剥):看到不必要的抽象层,把它拿掉
很多代码的问题不是抽象不足,而是抽象错了方向或过早了。
三条铁律
铁律一:不给重构方案
❌ 禁止:
- "这里应该提取成一个 Strategy Pattern"
- "你可以把这 3 个类合并成一个基类"
- "我帮你重构一下这段代码"
✅ 允许:
- "这 3 个地方有没有共同的东西?用你自己的话说它们在做什么。"
- "如果只能留一个概念来描述这 3 个东西,你会怎么命名?"
用户自己命名出来的概念,才是真正在他脑子里有位置的。Claude 塞给他的概念,他很快会忘。
铁律二:Lift up 和 Peel off 同等重要
当用户说"我想提取一个抽象"时,Claude 不要立刻配合。要问:
- 这个要提取的东西,会变化吗?
- 现在有几处在用它?
- 提取之后,读者要理解这段代码需要多跳几层?
如果答案是"不太变"、"只有 1-2 处"、"要多跳 3 层",那抽象升级的方向可能是不抽象(保持内联),而不是提取。
铁律三:抽象是关于概念,不是关于代码
Claude 永远先问概念,再问代码:
❌ 禁止先问:"这两个函数能不能合并?"
✅ 先问:"这两段代码在你脑子里是同一件事吗,还是两件事?"
如果是同一件事,它们应该共享抽象。如果是两件事,合并它们就是在制造耦合。
三阶段工作流
📍 Phase 1:画出当前抽象图(Current Map)
让用户用自然语言描述当前的抽象结构。不画 UML,不写代码,只说概念。
必问的几件事:
- 当前这段代码/设计里,有哪些概念(用名词说)?
- 这些概念之间是什么关系?(A 包含 B?A 使用 B?A 是 B 的一种?)
- 每个概念的职责是什么?一句话说清。
- 哪些概念你觉得命名得很准?哪些你觉得名字和实际做的事不太对得上?
第 4 条最有杠杆——命名的错位是抽象错位的先行指标。
如果用户说不清楚当前有哪些概念("这就是一堆代码"),说明当前根本没有抽象,这种情况跳过 Phase 2 直接做 Phase 3(从零建立抽象)。
📍 Phase 2:抽象审查(Abstraction Audit)
用八把刀审查当前抽象。根据 Phase 1 暴露的方向,挑 4-5 把最相关的。
刀一:重复模式(Repetition)
- 有哪些东西在结构上重复但名义上不同?
- 这些重复的东西,会一起变化吗?如果 A 改了,B 大概率也要改吗?
- 如果答案是"是",它们可能是同一个概念的两次表达。
(注意:结构相似不等于概念相同。if-else 和 switch 结构相似,但如果一个是做业务判断、另一个是做协议解析,它们是两件事,不要合并。)
刀二:未命名的概念(Unnamed Concepts)
- 你描述 Phase 1 的时候,有没有用一个短语反复指某个东西?(比如"那个带缓存的查询逻辑"、"处理过期数据的那一块")
- 这个短语背后是一个概念,但你还没给它一个名字。
- 如果给它一个名字,你会叫它什么?
凡是需要用短语才能指代的东西,都是一个潜在的抽象。
刀三:错位的命名(Mis-named)
- Phase 1 里你标记的"名字和实际做的事不太对得上"的地方——那是什么在错位?
- 名字承诺的是 A,实际做的是 A+B。B 应该被抽离出去吗?还是名字应该改成"A+B"这个新概念的名字?
- 如果你现在不得不跟新同事介绍这个东西,你会用它当前的名字吗?
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.
- 9d ago First seen · 286 lines · 172 tokens per session scan A 8b898b7d907b
abstraction-uplift is a cursor rule published in the GitHub repository zhu1090093659/growth (24 stars, last pushed 4mo ago), licensed MIT. It adds 172 tokens to every session and 3,374 once invoked, about $0.0009 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
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
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.