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/tysoncung/notion-agent-hub/cursorrulesgit clone --depth 1 https://github.com/tysoncung/notion-agent-hubWhat 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 | $0.00437 | $0.00437 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
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 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.
What it actually says
Cursor Rules for Notion Agent Hub
Project Context
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
Code Style
- TypeScript strict mode
- ES modules (import/export, .js extensions in imports)
- Zod for input validation
- Functional style preferred over classes
- Descriptive variable names, JSDoc comments on exports
MCP Patterns
- Tools are registered via
server.tool()with Zod schemas - Tool handlers return
{ content: [{ type: "text", text: string }] } - Errors return
{ content: [...], isError: true } - Server uses stdio transport (stdout reserved for MCP)
- All logging goes to stderr via the logger utility
Notion API
- Use @notionhq/client for all Notion operations
- Singleton client via
getNotionClient() - Handle rich_text arrays with
richTextToPlain()/plainToRichText() - Page properties vary by type — check
prop.typebefore accessing - Database queries support filters, sorts, and pagination
File Organization
src/tools/— Individual MCP tools (one per file)src/agents/— Agent workflows that compose toolssrc/queue/— Task queue for Notion DB pollingsrc/utils/— Shared utilities (Notion client, logger)tests/tools/— Vitest unit tests with mocked Notion client
Testing
- Use vitest for testing
- Mock the Notion client in tests (vi.mock)
- Test tool functions directly, not MCP handlers
- Each tool has its own test file
Environment Variables
- NOTION_API_KEY — Required for Notion operations
- NOTION_DATABASE_ID — Default database for task queue
- OPENAI_API_KEY — Optional, for content generation
- BRAVE_API_KEY — Optional, for web search
- LOG_LEVEL — debug | info | warn | error (default: info)
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 First seen · 46 lines · 437 tokens per session scan A 69cd3695521c
cursorrules is a cursor rule published in the GitHub repository tysoncung/notion-agent-hub (7 stars, last pushed 5mo ago), licensed MIT. It adds 437 tokens to every session, about $0.0022 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 2026-08-31.
Other cursor rules, from other repositories
agoragentic-integrate
Connect an external agent host, framework, tool, or specialist engine to Agoragentic governance and receipts. Use for adapters, lifecycle mapping, MCP/tool discovery, and bounded integration design.
cursorrules
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
qa-agent
QA workflow for reviewing stories, designing tests, and reporting verified defects.
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
clarify-first-prompting
Clarify-first strategy: detect ambiguity, ask targeted questions, expand simple prompts into detailed specifications.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.