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/TashanGKD/tashan-cursor-skillsWrote 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/tashangkd/tashan-cursor-skills/product-alignment-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/product-alignment-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/product-alignment-guard/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/tashangkd/tashan-cursor-skills/product-alignment-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/product-alignment-guard.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 | $0.00105 | $0.01725 |
| Opus 5 | $0.00053 | $0.00863 |
| Sonnet 5 | $0.00021 | $0.00345 |
| Haiku 4.5 | $0.00011 | $0.00172 |
Grade A, and why
product-alignment-guard 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品对齐守门规则(product-alignment-guard)
核心问题: ① 技术上「修好了」,但用户体验反而变差了(选了最方便的技术方案,不是最符合产品意图的) ② 一个看起来技术等级低(P2)的 Bug,实际上破坏了产品的核心价值承诺 ③ 修复者不知道「这个功能对用户意味着什么」,所以无法判断修复方向是否正确
触发条件
以下任一情况,此规则激活(在执行之前检查):
-
修复角色(fixer / 开发角色)准备修改「用户可见行为」的代码
- 用户界面交互
- AI 响应风格/格式/内容
- 用户数据流(写入/读取/展示)
- 权限/访问控制
-
Bug 分级为 P2 但涉及以下领域:
- 产品诚信(用户可能被误导)
- 身份标识(谁在说话/是否是 AI)
- 认知飞轮关键节点(Proposal 审批/L1 更新/L1.5 提炼)
-
准备做「快速技术修复」而没有查阅产品定义
触发后立即执行
Step P1: 确认产品定义已读
检查:本轮对话中是否已读取过产品定义.md?
IF 未读:
Read: 项目群/[项目]/产品经理/产品定义.md
重点读:与当前修复相关的功能章节
IF 找不到产品定义:
→ 输出警告:「⚠️ [product-alignment-guard] 找不到产品定义。
当前修复是否影响用户可见行为?
如影响:需要产品定义支持,暂不做此修复
如不影响(纯技术,如日志/性能/错误处理):可继续」
→ 等待确认
Step P2: 产品对齐检查(三个问题,任一答「是」则触发升级)
问题 1:「这个修复是否改变了产品的核心价值承诺?」
例:Proxy 模式出现第一人称 → 破坏「你在访问他人的认知」这一承诺 → YES
例:SQL 查询加了索引 → 性能提升,不影响承诺 → NO
问题 2:「这个修复是否涉及产品诚信?(用户是否会被误导)」
例:NPC 分身无 AI 标注 → 用户以为在与真人对话 → YES(即使技术上 P2)
例:按钮颜色偏差 → 视觉问题,不涉及诚信 → NO
问题 3:「我打算选择的修复方案,是「最方便的技术方案」还是「最符合产品意图的方案」?」
这两者相同 → 继续
这两者不同 → 必须选「最符合产品意图的」,即使技术上更复杂
IF 任一答案触发升级:
→ 输出:「⬆️ [product-alignment-guard] 此 Bug 需升级为产品优先级
原因:[触发的问题 + 具体说明]
在继续之前,确认:
① 产品定义中对此功能有明确要求
② 修复方案符合产品定义的设计意图(不只是让测试通过)」
Step P3: 修复方案对齐确认
在确定修复方案后,对照产品定义检查:
□ 修复后的行为是否符合产品定义中对此功能的描述?
□ 修复是否保持了功能的用户价值(不只是让测试通过)?
□ 是否有「设计强制项」或「产品诚信约束」被此修复影响?
IF 有不符合:
→ 调整修复方案,直到满足产品对齐要求
→ 如果技术限制使得产品对齐无法实现:
→ 写入产品问题追踪台(这是产品设计需要决策的地方,而不是技术修复的地方)
「产品设计问题」与「实现 Bug」的判断树
问:如果完美实现了当前的设计方案,用户体验是否符合产品意图?
YES → 这是「实现 Bug」(代码没有做到设计要求做的事)
→ 技术修复,fixer 正常处理
NO → 这是「产品设计缺陷」(设计本身有问题)
→ 不允许用技术方案填坑
→ 写入产品问题追踪台,等 PM 决策
典型场景举例
| 场景 | 技术分级 | 产品分级 | 正确处理 |
|---|---|---|---|
| Proxy 模式偶尔说「我认为」 | P2(功能可用) | P0(产品诚信) | 立即修复,产品第一人称是强制禁止项 |
| NPC 分身没有 AI 徽章 | P2(视觉问题) | P0(产品诚信) | 立即修复,这是产品诚信强制项 |
| 认知构建完成但 L0 不更新 | P1(功能错误) | P0(认知飞轮断裂) | 立即修复,这是认知飞轮核心节点 |
| 试用计数在免费大脑也显示 | P1(逻辑错误) | P0(用户被误导) | 立即修复,影响变现信任 |
| 按钮间距不标准 | P3(视觉) | P2(体验) | 正常排期,不升级 |
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.
- 10d ago First seen · 145 lines · 105 tokens per session scan A c780e2747ca8
product-alignment-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 105 tokens to every session and 1,725 once invoked, about $0.0005 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
10-feature-development
Feature implementation workflow and engineering mindset.
11-template-conventions
Reusable building blocks shipped with this template - use them instead of writing new ones.
03-ui
UI, layout, theming and localization standards.
09-android-best-practices
Android engineering best practices.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.