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/proactive-skills.manual-review-entry)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/proactive-skills.manual-review-entry"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/proactive-skills.manual-review-entry/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/proactive-skills.manual-review-entry"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/proactive-skills.manual-review-entry.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 | $0.04382 |
| Opus 5 | $0.00000 | $0.02191 |
| Sonnet 5 | $0.00000 | $0.00876 |
| Haiku 4.5 | $0.00000 | $0.00438 |
Grade A, and why
proactive-skills.manual-review-entry 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 today.
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.
2. **首選（DEFAULT）**：auto-triage 後 `bucket=ready` → **先跑 § 交付入口前置查詢的兩條指令**（`review-gui-service.sh status` ＋ `curl /api/changes`）： How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proactive Skills — 人工檢查入口
從 [[proactive-skills]] § Manual Review 抽出（2026-07-31）。主檔留的是 always-load 的三條契約（第一動作是 auto-triage、推進完 MUST 跑 gate script、NEVER 自判 bucket）；本檔是真的走到
## 人工檢查階段時的操作層。
## 人工檢查 的 checkbox 不能由 agent 自行代勾。
MUST 進入人工檢查階段（implementation tasks 完成、剩 ## 人工檢查 區塊）時，第一動作是 auto-triage（per [[review-gui-surface]] MUST 9），不是直接把 review-gui 連結丟給使用者。
Auto-triage + mechanical readiness gate
-
逐條讀 pending leaf item 的 annotation，判斷阻塞原因並自行推進：
（fix-requested）→ dispatch/wt修 code → merge-back → 重拍截圖 → strip annotation- evidence missing → 走 [[agent-self-verification]] fallback chain 收 evidence
（issue:）無(claude-analyzed:)→ triage issue 走 (A)-(E) 路由
-
推進完畢後 MUST 跑 mechanical gate script 確認 bucket：
node ~/offline/clade/vendor/scripts/check-review-readiness.ts \ --repo . --change <work-slug>- exit 0 → 可引導 user 到 review-gui
- exit 1 → 繼續 auto-triage 或如實報告卡住原因
- NEVER 自判 bucket、NEVER 跳過 script
NEVER 在 script exit ≠ 0 時引導 user 到 review-gui — orchestrator 自判已多次證明不可靠（同根因 pitfall 見 [[review-gui-surface]]）。
NEVER 預設用 native structured user-input surface 在 chat 內逐項彈對話框走人工檢查——那是 review-gui 不可用時的 fallback，不是 default path。
正確流程：
- Auto-triage first：推進所有 orchestrator 可處理的 pending items（fix-requested / evidence missing / issue triage）
- 首選（DEFAULT）：auto-triage 後
bucket=ready→ 先跑 § 交付入口前置查詢的兩條指令（review-gui-service.sh status＋curl /api/changes）：- 第 1 條 exit 0 且第 2 條印出了自己那條
changeKey（常態）→ NEVER 叫 user 跑任何啟動指令， 直接照 § 交付入口前置查詢表格第 1 列給 URL（host ＋ API 回的reviewPath，要指到某條 item 就加?item=%23N.M）。NEVER 在此另行憑印象拼一次 URL - exit ≠ 0，或清單裡沒有自己那條 → 走 § 交付入口前置查詢的第 2、3 列：自己把服務帶起來 /
重生
consumers.local再給 URL，NEVER 把啟動指令交給 user（聚合機制與 cwd 規約見 [[review-gui-surface]]）
- 第 1 條 exit 0 且第 2 條印出了自己那條
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.
- today Changed · +4 lines 040dfcf87b71
- 3d ago Changed · +2 lines 4d52f06776ab
- 7d ago First seen · 159 lines · 0 tokens per session scan A bbd7b30d3cb1
proactive-skills.manual-review-entry 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 4,382 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
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.