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/leadmagic/smartlead-mcp-server/api-patternsgit clone --depth 1 https://github.com/LeadMagic/smartlead-mcp-serverWhat 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 | $0.00000 | $0.03222 |
| Opus 5 | $0.00000 | $0.01611 |
| Sonnet 5 | $0.00000 | $0.00644 |
| Haiku 4.5 | $0.00000 | $0.00322 |
Grade A, and why
api-patterns scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ 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.
How it starts
The opening of the file, as written. The whole thing โ 423 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
name: SmartLead MCP API Development Patterns description: Development patterns for API clients and MCP tools in the SmartLead server author: LeadMagic Team version: 1.0.0
๐๏ธ SmartLead API Development Patterns & Best Practices
Developer Guide: Master the patterns and practices used throughout the SmartLead MCP Server. This guide will help you write consistent, maintainable code that follows our established conventions.
๐ฏ Quick Reference
๐ฅ Most Important Patterns
- Base Client Extension โ All API modules extend
BaseSmartLeadClient - MCP Tool Registration โ Use the standard registration pattern
- Zod Schema Validation โ All inputs validated with Zod
- Error Handling โ Use
SmartLeadErrorfor API errors - Type Safety โ Avoid
any, use proper TypeScript types
๐๏ธ SmartLead API Client Architecture
๐ ๏ธ Base Client Pattern
File:
src/client/base.ts
The foundation of all API interactions:
export abstract class BaseSmartLeadClient {
protected config: SmartLeadConfig;
constructor(config: SmartLeadConfig) {
this.config = config;
}
// ๐ Automatic retry with exponential backoff
protected async withRetry<T>(operation: () => Promise<T>): Promise<T> {
// Handles transient failures automatically
}
// ๐ HTTP methods with proper typing
protected async get<T>(url: string): Promise<T> { }
protected async post<T>(url: string, data: unknown): Promise<T> { }
protected async put<T>(url: string, data: unknown): Promise<T> { }
protected async delete<T>(url: string): Promise<T> { }
}
Key Features:
- โ HTTP request handling with Axios
- โ Automatic retry logic with exponential backoff
- โ Rate limiting and request queuing
- โ Error handling with SmartLeadError class
- โ Request/response logging for debugging
๐ Module Structure Pattern
Example:
src/modules/campaigns/client.ts
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 ยท 423 lines ยท 0 tokens per session scan A e700f4980bf9
api-patterns is a cursor rule published in the GitHub repository LeadMagic/smartlead-mcp-server (21 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,222 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
bmad-orchestrator
This rule is triggered when the user types @bmad-orchestrator and activates the BMad Master Orchestrator agent persona.
analyst
This rule is triggered when the user types @analyst and activates the Business Analyst agent persona.
architect
This rule is triggered when the user types @architect and activates the Architect agent persona.
bmad-master
This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.
dev
This rule is triggered when the user types @dev and activates the Full Stack Developer agent persona.
qa
This rule is triggered when the user types @qa and activates the Test Architect & Quality Advisor agent persona.