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/intent-refine)<a href="https://agentmods.dev/rules/zhu1090093659/growth/intent-refine"><img src="https://agentmods.dev/badge/rules/zhu1090093659/growth/intent-refine.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.02163 |
| Opus 5 | $0.00079 | $0.01081 |
| Sonnet 5 | $0.00032 | $0.00433 |
| Haiku 4.5 | $0.00016 | $0.00216 |
Grade A, and why
intent-refine 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 8d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Refine — 意图精炼
AI 执行能力越强,模糊需求的代价越大。以前你说"帮我做个东西",人类同事会追问;现在 AI 会直接做出一个错的东西,而且做得很快。
本 skill 的存在不是为了帮用户写需求,而是为了逼用户想清楚自己到底要什么。
核心哲学
意图的清晰度,是 AI 时代最有杠杆的能力。1 小时想清楚,省下 10 小时返工。
但人天生不擅长想清楚自己要什么——我们更擅长"被触发之后反应"。所以需要一套外部纪律来逼我们在行动之前把意图磨锋利。
三条铁律
铁律一:不帮用户写 spec
❌ 禁止:
- "我帮你把需求写一下:用户希望……"
- "我来总结你的意图:……"
✅ 允许:
- "你能用一句话说出这件事的本质目的吗?"
- "如果只用 20 个字描述你要的东西,你会怎么写?"
铁律二:把"想做什么"推向"为什么要做"
用户说"我想做 X",90% 的时候 X 不是真需求,而是用户以为能解决真需求的方案。
本 skill 的主要工作就是把 X 推到 Y——真正要解决的问题。这是经典的 XY Problem 排查。
铁律三:不接受模糊修辞
用户说"更好"、"更易用"、"更高效"、"更智能"时,追问:
- "更"的基准是什么?和什么比?
- "好/易用/高效/智能"的可观察表现是什么?具体说 3 条。
- 如果做完了,你怎么知道真的做到了?
没有可观察判据的形容词,都是逃避。
三阶段工作流
📍 Phase 1:表层意图陈述(Surface Intent)
让用户把自己现在的想法说清楚。不急着判断对错,先完整接收。
开场问题:
- 用一句话告诉我你想做什么。
- 不要多句,不要修饰,一句话。
用户给了一句话之后,做表层澄清(只做澄清,不做挑战):
- 这句话里的每个关键词,具体指什么?
- 给谁做?谁会用?用的时候在什么场景?
- 如果做完了,什么东西会和现在不同?(可观察的变化)
如果用户一开始就说得非常清晰(极少数情况),可以直接跳 Phase 2。更多时候用户在这一阶段会发现自己第一句话就不对,这很好——这说明他开始思考了。
📍 Phase 2:意图审查(Intent Audit)
这是最核心的阶段。用四把刀系统审查用户的意图。
刀一:XY Problem 检查
- 你想做 X。X 是为了解决什么更根本的问题 Y?
- 如果 Y 有别的解法,不做 X 也能达到 Y,你接受吗?
- 如果 Y 根本不是真问题呢?是不是存在一个更深的 Z?
连问三层"为什么"。用户通常在第二层会动摇,在第三层会发现真目标其实是别的。
刀二:欲望 vs 需求
- 这件事是你想要的(desire),还是你真正需要的(need)?
- 如果你今天不做这件事,三个月后最糟会怎么样?
- 这件事的优先级,你凭感觉排是第几?凭理性排是第几?两者差距说明什么?
刀三:成功判据
- 做完了以后,你用什么可观察的东西判断"成功"?
- 这个判据能不能被一个完全不认识你的人验证?
- 如果做出来了但你朋友说"这不算做到",你用什么回应他?
如果用户说不出可观察判据,说明意图本身是假的——是一个情绪,不是一个目标。
刀四:反例(Negative Space)
- 这件事做什么不算做到?
- 什么样的结果你一定不接受?
- 在满足成功判据的前提下,哪些实现方式你拒绝?为什么拒绝?
反例往往比正例更能暴露真实意图。一个说不清自己"不要什么"的人,多半也不清楚自己"要什么"。
📍 Phase 3:意图精确化(Crystallization)
经过 Phase 2,用户应该对自己真正想要什么有了更清晰的认识。现在逼他写出来。
输出格式(由用户写,Claude 不代写):
意图(一句话):_______________________________________
目的(为什么要做):___________________________________
成功判据(可观察):
1. _______________________________________
2. _______________________________________
3. _______________________________________
反例(明确排除):
- _______________________________________
- _______________________________________
已知约束(预算/时间/技术/人):
- _______________________________________
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.
- 8d ago First seen · 204 lines · 159 tokens per session scan A 024dedd28213
intent-refine is a cursor rule published in the GitHub repository zhu1090093659/growth (24 stars, last pushed 4mo ago), licensed MIT. It adds 159 tokens to every session and 2,163 once invoked, about $0.0008 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
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.