Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gargoyle92/agentify-mcpnpx agentmods add rules/gargoyle92/agentify-mcp/03-typescript-safetyWrote 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/gargoyle92/agentify-mcp/03-typescript-safety)<a href="https://agentmods.dev/rules/gargoyle92/agentify-mcp/03-typescript-safety"><img src="https://agentmods.dev/badge/rules/gargoyle92/agentify-mcp/03-typescript-safety/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/gargoyle92/agentify-mcp/03-typescript-safety"><img src="https://agentmods.dev/badge/rules/gargoyle92/agentify-mcp/03-typescript-safety.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 | $0.01226 |
| Opus 5.5 | $0.00000 | $0.00490 |
| Sonnet 5.5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
03-typescript-safety 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
03-TypeScript-Safety
Type System Configuration
The project uses strict TypeScript configuration in tsconfig.json with ESNext modules and strict type checking.
Central Type Definitions
All types are centrally defined in types/index.ts and must be imported from there.
CRITICAL TYPE SAFETY RULES - MUST FOLLOW
✅ ALWAYS DO:
- Import from central types:
import { AgentClient, AgentStatus } from '../types/index.js' - Use strict type annotations: Define return types for all public methods
- Validate enum usage: Always use enum values, never string literals
- Type guard functions: Implement type guards for runtime type checking
- Generic constraints: Use proper generic constraints for extensibility
❌ NEVER DO:
- Use
anytype: Avoidany- useunknownor proper types instead - Skip type annotations: Never omit return types on public methods
- String literal enums: Use enum values like
AgentStatus.CONNECTED, not'connected' - Bypass type checking: Never use
as anyor@ts-ignorewithout justification - Ignore nullable types: Always handle undefined/null cases explicitly
Enum Usage Standards
✅ CORRECT Enum Usage:
// Import from central types
import { AgentClientType, AgentStatus } from '../types/index.js';
// Use enum values
client.status = AgentStatus.CONNECTED;
if (client.type === AgentClientType.CLAUDE_CODE) { ... }
// Type-safe enum iteration
Object.values(AgentClientType).forEach(type => { ... });
❌ INCORRECT Enum Usage:
// Bad - string literals
client.status = 'connected';
if (client.type === 'claude-code') { ... }
// Bad - hardcoded values
const types = ['claude-code', 'gemini-cli'];
Interface Implementation Standards
Required Interface Patterns:
// Tool definitions must implement ToolDefinition
export interface ToolDefinition {
name: string;
description: string;
inputSchema: {
type: string;
properties: Record<string, any>;
required?: string[];
};
clientTypes?: AgentClientType[];
handler: (args: any, client: AgentClient) => Promise<any>;
}
// Resource definitions must implement ResourceDefinition
export interface ResourceDefinition {
uri: string;
name: string;
description: string;
mimeType: string;
clientTypes?: AgentClientType[];
handler: (client: AgentClient) => Promise<any>;
}
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.
- 2mo ago First seen · 204 lines · 0 tokens per session scan A bd1d1c1eaf75
03-typescript-safety is a cursor rule published in the GitHub repository gargoyle92/agentify-mcp (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,226 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 2026-08-31.
Other cursor rules, from other repositories
vue-typescript-patterns
A set of coding rules for Vue 3 projects using TypeScript, a language that adds type checking to JavaScript. It covers component structure, file locations, TypeScript usage, and Pinia, a library for shared application state.
nextjs-typescript-app-cursorrules-prompt-file
Cursor rules for Next.js development with TypeScript integration.
ts
A set of TypeScript coding rules covering types, naming, file organization, error handling, and strict type checking. TypeScript is JavaScript with checks that help catch many mistakes before the program runs.
typescript-security
A secret scanner owns hardcoded keys. Read secrets from the environment and fail startup when a required one is missing.
general-rule
Cursor rule "general-rule" from vinhnx/vtchat, covering development guidelines, tech stack & project overview, package management, code style and ui/ux design principles.
naming-conventions-rule
A small set of naming rules for TypeScript, Node.js, and Next.js projects. It defines how directories and React components should be named and exported.