Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starternpx agentmods add rules/yudefine/nuxt-supabase-starter/manual-review.backendWrote 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/manual-review.backend)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/manual-review.backend"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/manual-review.backend/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/manual-review.backend"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/manual-review.backend.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 | $0.06230 |
| Opus 5 | $0.00000 | $0.03115 |
| Sonnet 5 | $0.00000 | $0.01246 |
| Haiku 4.5 | $0.00000 | $0.00623 |
Grade A, and why
manual-review.backend scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
當 `proposal.md` 宣告 `**No user-facing journey (backend-only)**` 時，`## 人工檢查` 區塊適用更嚴的規約 — **只**允許三類項目（production 授權 / 商業判斷 / production 觀察），其餘 SSH / psql / curl / schema 驗證等 evidence collection **MUST** 寫進新的 `## N. Backend How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime adapter boundary
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability it can prove; an absent or unverified capability remains blocked and MUST NOT be silently replaced by a neighbouring runtime.
Manual Review — Backend Verification Flow
Reference 檔。核心規約見
manual-review.md。本檔聚焦 backend-only change 的人工檢查特別規約，與所有 verify channel 的標準流程（含[verify:e2e]/[verify:api]/[verify:ui]/ multi-marker /[review:ui]flow /[discuss]flow / 混合 kind change），以及 dispatch 前必驗的 pre-verify baseline。
Backend-only change 的特別規約
當 proposal.md 宣告 **No user-facing journey (backend-only)** 時，## 人工檢查 區塊適用更嚴的規約 — 只允許三類項目（production 授權 / 商業判斷 / production 觀察），其餘 SSH / psql / curl / schema 驗證等 evidence collection MUST 寫進新的 ## N. Backend Verification Evidence section 由 apply 階段 session owner 自跑自貼，禁止塞進 ## 人工檢查 讓使用者扛。
完整規約（含三類定義、## N. Backend Verification Evidence 模板、例外宣告固定文字、反面範例）見 ux-completeness.md 的「必填 Backend-only Manual Review 規約」。manual-review.evidence.md 的「動詞 → 結果」格式只適用於有 user-facing journey 的 change。
標準流程
依 item 的 kind marker 走不同 flow。MUST 覆蓋 verify channels、[review:ui]、[discuss] — 一個 change 的 ## 人工檢查 區塊可同時包含多種 kind 的 items。
[verify:*] flow（/implement 收尾的 Verify Channel Pass）
tasks 檔有未勾 [verify:e2e] / [verify:api] / [verify:ui] / multi-marker items 時，/implement 收尾 MUST 依 channel 分流處理每一條，不是只跑最後一條。Cookbook 與範本見 vendor/snippets/verify-channels/README.md。
[verify:e2e] channel
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 74f22a99a7a7
- 2d ago Changed · +8 lines 7d859e7bf0db
- 6d ago First seen · 230 lines · 0 tokens per session scan A 175bf520d994
manual-review.backend is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,230 tokens. A static security scan graded it A with 1 finding (makes network calls). 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
api-validation-workflow
Integrates API validation tools (OpenAPI spec retrieval and HTTP request testing) into the development workflow, enabling autonomous testing and validation of features. This rule defines when and how to use API validation tools for continuous validation, debugging, and quality assurance throughout the development…
routers_tests
Since this is a FastAPI web application, test logic for API endpoints often involves checking status codes. Remember, when making a request to an API endpoint, you should specify the followredirects parameter. With followredirects=False, the response code will often be 303; otherwise it will be the response code of…
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.