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/codebase-memory-index.freshness)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/codebase-memory-index.freshness"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/codebase-memory-index.freshness/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/codebase-memory-index.freshness"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/codebase-memory-index.freshness.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 | $0.00786 |
| Opus 5 | $0.00000 | $0.00393 |
| Sonnet 5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
codebase-memory-index.freshness 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.
What it actually says
codebase-memory index 保鮮的機械層
本檔是 [[codebase-memory-index]] 的 path-scoped sibling。三條 NEVER（裸跑 CLI／繞過 wrapper／ 把
auto_index・auto_watch設回 true）留在常駐層，NEVER 因為本檔沒載入就當作可以裸跑。
| 已接通的 Claude hook | 覆蓋 |
|---|---|
post-bash-cbm-index-refresh.sh / native PostToolUse |
比對當下 HEAD 與 provenance；已有索引且 working tree 乾淨時，背景更新過期索引 |
session-start-cbm-index-check.sh / native SessionStart |
同一健康判定，涵蓋人手動 commit、rebase / pull；缺索引、未知來源、dirty 或失敗時提示，同 session 狀態不變不重複 |
上表的自動觸發以該產品入口已安裝、啟用並驗證 hook 為前提。Codex／Cursor 的 hook adapter
存在不代表這兩支 handler 已接通。沒有該入口的自動檢查證據時，agent 在首次使用圖譜前，
從目前 repo 執行 bash ~/offline/clade/plugins/hub-core/hooks/session-start-cbm-index-check.sh，
讀取提示再決定是否經 wrapper 更新；commit／rebase／pull 後若還要查圖譜，再做相同檢查。
Clade 不在預設位置時使用其實際 checkout 路徑。檢查程式缺席或無法執行就回報保鮮未驗，
不把缺少自動觸發當成 index 新鮮，也不啟用 auto_index／auto_watch 補洞。
改動 config 或 wrapper 參數前先讀 [[pitfall-cbm-auto-index-concurrent-oom]]。
| REQUIRED 欄位 | 內容 |
|---|---|
| 觸發條件 | session-start-cbm-index-check.sh 在 index 落後 HEAD 或 DB 缺失 / 不可讀、dirty 或 provenance 不明時提示。提示不 block；已有索引且乾淨的過期 HEAD 自動背景刷新，缺索引仍由 bootstrap 或 wrapper 建立 |
| 消費端 | 要用 search_graph / trace_path / get_code_snippet 的 agent（讀提示決定要不要先 index）；Claude hooks、Codex / Cursor 原生投影與 Pi extension 共用 cbm-health.ts |
| 載入路徑 | 本檔由共同 rules planner 交付到所選 runtime 的原生規約入口；Claude 為 .claude/rules/codebase-memory-index.md，Codex baseline 為 AGENTS.md，Cursor 為 .cursor/rules/；clade home 經 .claude/rules/local/ pointer。規約載入與 hook 自動觸發分別驗證 |
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 First seen · 35 lines · 0 tokens per session scan A 128f780eebee
codebase-memory-index.freshness 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 786 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 2026-09-11.
Other cursor rules, from other repositories
synapse
Rules for using Synapse MCP — prefer the graph over grep.
Performance-Issues
Investigates and diagnoses performance issues, identifying bottlenecks in code execution, slow queries, high resource consumption (CPU, memory), or network latency.
bug-fix
Light skill: TDD pipeline for bug fixes. Regression test first, then fix. Can auto-invoke when the user reports a bug, describes unexpected behavior, or asks to fix an issue.
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.