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/snowdreamtech/template/cursorrulesgit clone --depth 1 https://github.com/snowdreamtech/templateWhat 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 | $0.00361 | $0.00361 |
| Opus 5 | $0.00180 | $0.00180 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
cursorrules 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.
What it actually says
🚨 CRITICAL SYSTEM INSTRUCTION 🚨
Before answering ANY prompt or executing ANY code in this repository, you MUST first read and strictly adhere to ALL the rules defined in the following directory:
Rules Location
📁 .agent/rules/
🚨 CRITICAL TOKEN LIMIT PROTOCOL 🚨
Do NOT load all files in .agent/rules/ simultaneously. You will exceed the context window.
You MUST follow this strict loading sequence:
- Load Core Fundamentals: Always read
01-general.mdthrough12-docs.md. - Consult the Lazy-Loading Router: Read
.agent/rules/00-index.mdto discover technology-specific rules. - Load On Demand: Based on the index, load ONLY the specific
.mdfiles relevant to your current task (e.g.,react.mdfor a React task).
Why This File Exists
This project uses a unified rule system to ensure consistent AI behavior
across all AI-powered IDEs and tools (Cursor, Windsurf, GitHub Copilot,
Cline, Claude, Gemini, Trae, Roo Code, Augment, Amazon Q, Kiro,
Continue, Junie, etc.). This file is a redirect entry point —
the actual rules live in .agent/rules/ as the Single Source of Truth.
Failure to follow the rules inside
.agent/rules/and the Lazy-Loading protocol is completely unacceptable.
Slash Commands / Workflows
All AI slash commands and standard operating procedures (SOPs) are located in .agent/workflows/. If the user invokes a command like /speckit.plan, execute the corresponding markdown file in that directory.
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 First seen · 34 lines · 361 tokens per session scan A fdeeed611a38
cursorrules is a cursor rule published in the GitHub repository snowdreamtech/template (15 stars, last pushed yesterday), licensed MIT. It adds 361 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other cursor rules, from other repositories
agent-routing.pi-input-intercept
Codex 模型經 Pi machine dispatch 提出問題時的攔截、評估、代答或升級 protocol；觸及 spectra change / screenshot 情境時 path-scoped 載入.
auth-data-path-consistency
Auth 策略與資料存取路徑一致性——防止混合 auth 狀態導致 silent 權限降級.
vk-org-resolution
VirtualKey org resolution has TWO join chains (Project for application VKs, Owner for personal VKs); vkSelectSQL must COALESCE both or personal VKs silently return NULL org.
design-tokens
Visual values via CSS variables; no hex / rgb literals in style.
agent-routing.pi-watch-protocol
Pi 派工的標準流程模板、Pi Watch Protocol、Plan-first / Git baseline declaration、$spectra-apply Runtime Gate、screenshot-review verify mode 派工與監看、配額耗盡的 fallback 鏈全文、Spectra Propose / Apply 的 dispatch 契約、Orchestration Residency 的四步做法、Routing Table 下推列（spectra 三列 + screenshot 兩列）的取證全文；apply 階段 / 觸及 spectra change 時 path-scoped…
i18n-mandatory
All user-visible UI text uses t('namespace:section.key') from react-i18next.