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/YuDefine/nuxt-supabase-starterWrote 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/yudefine/nuxt-supabase-starter/coupling-cohesion)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/coupling-cohesion"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/coupling-cohesion/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/yudefine/nuxt-supabase-starter/coupling-cohesion"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/coupling-cohesion.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 | $0.00000 | $0.03324 |
| Opus 5 | $0.00000 | $0.01662 |
| Sonnet 5 | $0.00000 | $0.00665 |
| Haiku 4.5 | $0.00000 | $0.00332 |
Grade A, and why
coupling-cohesion 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 yesterday.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coupling & Cohesion
SOLID 在 functional TS 語境的可測子集。這裡只收 S（內聚）、O（shotgun surgery）、D（依賴方向）—— L 與 I 在 composable-based 專案幾乎是空集合（沒有繼承層級就沒有 LSP 可違反；structural typing 下 ISP 自動成立大半），為它們寫 checklist 只會產出無法判定的條目。
三層分工
| 層 | 誰執行 | 管什麼 |
|---|---|---|
| Gate | vp lint（pre-commit vp-staged / CI） |
import/no-cycle、oxc/no-barrel-file —— 機械可判定、無爭議 |
| Signal | node scripts/audit-coupling-cohesion.ts |
change coupling、跨檔 discriminant switch —— 報告不擋 commit |
| Review | /code-review checklist |
職責語意判斷 —— 機械測不到的部分 |
Signal 層的輸出 NEVER 當 gate 用：跨檔規則在 staged-only 情境算不準，把它接進 pre-commit 只會 產出「改一行擋十次」的體驗，然後大家學會加 disable comment。
Review 層 checklist
本節純 review 層，無機械訊號。消費端是 code-review agent 的程式碼品質 checklist。規模門檻
（max-params / max-lines / complexity）不在本節、也不在 gate——理由見下方
§ 為什麼 gate 只有兩條規則。
與 § Shotgun surgery 的關係：本節管「一個函式做了幾件語意上不同的事」；Shotgun surgery 管 「同一個 discriminant 散落 ≥3 個檔」。兩層互補，不重複判準。
一個函式只做命令或只做查詢
一個函式 MUST 只做命令（改狀態）或只做查詢（回答案），NEVER 兩者兼具。
NEVER 讓 query / check 型函式藏副作用：checkPassword NEVER 順手初始化 session。名字說得出來
的操作 MUST 是它做的全部。
NEVER 用 boolean flag 參數切換行為
createUser(data, isAdmin) 把「這個函式做兩件事」藏進 call site。MUST 拆成兩個具名函式
（createAdminUser / createMemberUser）。
這條管的是切換行為的 flag，不是「選項物件裡的 boolean 欄位」。{ dryRun: true } 這種不改
呼叫哪條路徑的選項，不是本條的對象。
函式內分段註解 = extract-method 警報
函式體內出現 // Validation / // Calculation / // Persist 這類分段標籤時，每個被標籤的區塊
MUST 抽成具名函式，讓上層函式讀起來是一份目錄而不是實作。區塊順序 MUST 讓呼叫端由上往下讀就能
跟上故事——先做什麼、再做什麼，不要先跳進細節。
參數順序有歧義時包成參數物件
fn(user, true, 3) 這種位置參數，caller 對不到第 2、第 3 個是什麼時，MUST 改成參數物件。
NEVER 把參數個數寫成 0–2 的硬門檻——§ 為什麼 gate 只有兩條規則 已用對照專案否決 max-params。
Gate 判讀
import/no-cycle 炸了代表兩個模組互相依賴對方的具體實作。兩條標準拆法：
- 抽共用 type / 常數到第三個模組，雙方都 import 它（最常見，cycle 多半由共享的 type 或 registry 常數造成）
- 依賴反轉：把低層模組對高層的回呼改成參數注入，由高層在組裝時傳入
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.
- yesterday Changed · +1 lines 32104a80392e
- 5d ago First seen · 184 lines · 0 tokens per session scan A da4d58f8b5fd
coupling-cohesion is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,324 tokens. 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 2026-09-03.
Other cursor rules, from other repositories
validator_quality
Quality Validator — check for complexity, dead code, inconsistent naming, and technical debt.
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.