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/agent-routing.keepalive-wake)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/agent-routing.keepalive-wake"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/agent-routing.keepalive-wake.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 | $0.02913 |
| Opus 5 | $0.00000 | $0.01456 |
| Sonnet 5 | $0.00000 | $0.00583 |
| Haiku 4.5 | $0.00000 | $0.00291 |
Grade A, and why
agent-routing.keepalive-wake 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Routing — keepalive 醒來與 shared-action consent（reaction-time 契約）
Reference 檔。要不要排 keepalive（Iron Law、適用範圍窮舉、派出當下的自查表、Red Flags）留在
agent-routing.md§ 主線靜默上限；怎麼填（canonical inert 模板逐字、deadline 取值）與醒來之後做什麼都在本檔。兩個時刻各有 [[agent-routing]] 的具名時機指針叫醒本檔。
Generic keepalive 醒來只做控制面動作
| 可觀察 predicate | 動作 |
|---|---|
native non-blocking task-status query = running，且未到 deadline |
以完全相同的 inert prompt 重排既有 interval，本 turn 結束 |
| task = terminal | 停對應 wakeup，排一次不含原任務、結果或授權的 ASYNC_LIFECYCLE_HANDOFF task=<id> owner=<owner> cause=terminal |
| task = running，且到 deadline | 停 control wakeup、保留 owner 與 in-flight claim，排 ASYNC_DEADLINE_INTERVENTION；owner 必須先取消 task（native cancellation control）或取得具名延長，確認 terminal 前 NEVER 收割、釋放 lock 或重派 |
狀態不可判定（含 runtime 沒有 native task-status query 可用） |
不 claim、不收割、不釋放 lock；以同一 inert prompt 進行有限次重查。次數用盡時走 ASYNC_DEADLINE_INTERVENTION，確認 terminal 前同樣不得重派。NEVER 因為查不到狀態就改讀 BashOutput tail 或 log 補判——那是 allowlist 外的動作，per 下一段 |
control turn 的 allowlist 只有「native non-blocking task-status query、重排同一 inert wakeup、停止 wakeup、排 lifecycle handoff / deadline intervention」。NEVER 讀 repo / log 猜狀態、執行原任務、Edit / Write、commit、publish、propagate、push、開新工作或做任何 shared-resource mutation。
每一個 native completion notification 與 terminal lifecycle handoff MUST 先共用 claim（pending → harvesting → harvested）再收尾。claim key：有 harness task id 的路徑用 task-id；notification-only 路徑（taskId: null）用 owner ref，狀態機相同：已是 harvesting / harvested 則 no-op（這擋掉 delayed notification 重複收割），deadline / unknown 不得 claim。只有 claim 成功的正常 turn 可讀 result 並走 owner 既有收尾，且同一 turn MUST 停掉對應 wakeup（native wakeup scheduler({stop: true})）並一併 native cancellation control owner 的 persistent Monitor（若有）。
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 · +2 lines 19aac517a5d8
- 8d ago First seen · 88 lines · 0 tokens per session scan A 8d90e96b89b3
agent-routing.keepalive-wake 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 2,913 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 2026-08-30.
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.