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/checker-subagent)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/checker-subagent"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/checker-subagent/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/checker-subagent"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/checker-subagent.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 | $0.03384 |
| Opus 5 | $0.00000 | $0.01692 |
| Sonnet 5 | $0.00000 | $0.00677 |
| Haiku 4.5 | $0.00000 | $0.00338 |
Grade A, and why
checker-subagent 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 3d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checker Subagent（高擴散半徑改動複核）
核心命題：checker 買到的唯一東西是 fresh context——一顆沒看過實作過程的眼睛。這對「我剛才有沒有寫錯」幫助有限（模型自己就會抓到並修掉），但對「這個改動對我沒看過的地方做了什麼」是不可替代的。所以派不派 checker 的判準是擴散半徑：錯了會不會波及沒被改到的檔案、沒被改到的 repo。本規約定義何時必須派 checker、checker 收到什麼、以及主線拿 finding 怎麼辦。
Iron Law — 擴散半徑決定派不派
違反字面就是違反精神。
改動會落到多個 consumer、或會影響沒被改到的程式碼時，
寫它的 agent NEVER 是唯一判定它可以散播的人。
動跨 consumer 共用 SoT（rules/core/ 本體、vendor/scripts/ 散播層、plugins/hub-core/ skill、claude-md/ 注入段落）或高擴散半徑 consumer 資產（DB migration、auth 路徑、多處 import 的共用 util、對外 API contract）時，主線在 publish / propagate / commit 之前 MUST 派一個 fresh-context checker subagent。checker 使用目前 runtime 可建立的獨立上下文入口；實際工具與參數由該 runtime 的 checker adapter 指定。checker 不繼承 maker 的對話，不續跑 maker。若入口無法建立獨立上下文，回報具體能力缺口，保留未通過狀態。
Fresh context 與跨模型是兩個欄位：同模型的新上下文可以提供獨立複核，但不能據此宣稱已完成跨模型裁決。另有跨模型 gate 時仍依其指定模型與證據要求執行。
其餘任務 NEVER 派 checker。 這包含 ≥3 phase 的 change、effort: high+ 的單一任務、新 endpoint、新邏輯分支，以及任何「我想確認一下自己有沒有做對」的場景——模型會自行捕捉並修正自己的錯誤，額外派 agent 複驗只是把同一份判斷跑第二次，燒 token 不提升品質。
何時 REQUIRED
| 情境 | checker | 判準 |
|---|---|---|
動跨 consumer 共用 SoT（rules/core/ 本體 / vendor/ 散播層 / hub-* skill / claude-md/ 注入段） |
REQUIRED | 一炸全 fleet 同時撞 |
| 動高擴散半徑 consumer 資產（DB migration / auth 路徑 / 多處 import 的共用 util / 對外 API contract） | REQUIRED | 錯了會波及沒被改到的程式碼 |
其餘一切（≥3 phase change / effort: high+ / 新 endpoint / 邏輯分支 / refactor / typo） |
NEVER 需要 | 擴散半徑止於本次 diff；模型自行捕捉並修正 |
說不清是哪一格時的判準：問「這個改動如果錯了，會不會影響到我沒有改的檔案或別的 repo？」——答案是「不會」就不派。任務跑了幾個 phase、花了多久、有多難，都跟這個問題無關。
派 checker 的前置條件（MUST 先滿足）
派 checker 之前，[[verify-gate-chain]] 的 L0–L2 MUST 已經全綠（lint / typecheck / test 全 exit 0）。gate 紅著派 checker 是浪費——機械可判定的問題交給機械擋，checker 的 context 應該整份花在語意上。
gate 紅 → 先修，修完再派。NEVER 把 gate output 塞進 checker brief 當判定材料。
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.
- 3d ago Changed e7637928af14
- 7d ago First seen · 142 lines · 0 tokens per session scan A 3b58c6d371d3
checker-subagent 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 3,384 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
simple-design
Kent Beck's Four Rules of Simple Design - fundamental principles for writing clean, maintainable code. These rules are applied in priority order and work synergistically with TDD.
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.