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.
npx agentmods add rules/yudefine/nuxt-supabase-starter/commit.detailgit 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/commit.detail)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/commit.detail"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/commit.detail.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 | $0.00000 | $0.12988 |
| Opus 5 | $0.00000 | $0.06494 |
| Sonnet 5 | $0.00000 | $0.02598 |
| Haiku 4.5 | $0.00000 | $0.01299 |
Grade A, and why
commit.detail 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 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.
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 — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit（全文）
本檔是 [[commit]] 的下推全文。[[commit]] 常駐「強制入口 ＋ WIP 處置禁令 / 話術關鍵詞表」，其餘全部在這裡。
理由
/commit 封裝了品質閘門，繞過等於讓壞 code / 壞版本號 / 壞 tag 進 repo。各 gate 一行定性如下，MUST 全綠才能 commit；執行細節一律見 /commit skill（.cursor/skills/commit/SKILL.md）：
- 0-A 程式碼審查：simplify（序跑第一）→ GPT-5.6-sol via Pi（effort: xhigh，經 codex-review-safe.sh）跨模型 review → Critical / Major 條件升 max；修正一律由主線執行。配額耗盡（exit 4）→ 主線 foreground 自 review，且 MUST 明示「跨模型 gate 未達成」並登記待補；NEVER 改派 Claude subagent 充當跨模型 review（同池同模型，gate 實質為空），NEVER 靜默當作 0-A.1 通過。換池到 Cursor 池在 [[agent-routing]] 的 fallback 紀律上是正確形狀，但 TD-520 已確認該池的模型同 UID 且有 unrestricted Shell，拿到 OS 層隔離前 NEVER 用於 0-A.1
- 0-B UI Design Review（條件觸發）：
.vue模板 + 頁面/元件/佈局/互動/樣式變更時派 screenshot-review - 0-C format / lint / typecheck / test / doctor 全綠：
scripts.check不含 test → 額外跑pnpm test；scripts.doctor必裝（缺裝 = block commit，要求先安裝 vite-doctor）。oxfmt batched--check報未預期 diff 以單檔重跑為準（[[pitfall-oxfmt-batched-check-false-positive]]） - 0-D Doc Alignment（條件觸發）：diff 觸及 docs / rules / snippets / audit script / 業務碼 / bug fix 時，檢查 cross-ref / 路徑引用 / pitfall status / 三方受眾文件忠實度（含 VitePress sidebar）四面向
- 0-E evlog map 覆蓋率（條件觸發）：diff 觸及 entry point（
server/{api,routes,middleware,tasks}// pages / Next route handler）時跑 gate；@evlog/cli必裝（缺裝 = block commit，比照 doctor）。判定是 strict：整個 repo 的每一個 entry point 零失敗 check、零 suppression，不是只看本次 diff 觸及的那幾個 —— 既有 gap 一律要補 - 並行：simplify 序跑完後 0-A.1 / 0-B / 0-C 三軸 MUST 並行（除非 fast-path 跳過 0-A.1）；0-D / 0-E 在匯合後條件觸發
- Step 1 Schema 同步檢查 —
database.types.ts與 migration 對齊 - Step 5 版本號升級 + tag push —
feat→ minor、其他 → patch
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 · +10 lines e1244a85d66d
- 2d ago First seen · 437 lines · 0 tokens per session scan A 36b0619dad2f
commit.detail 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 12,988 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
workflow
Development workflow and commit practices.
cmd-build
Implement the next task incrementally — build, test, verify, commit.
speckit_speckit.git.commit
Proxy for the speckit.git.commit workflow.
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.