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/tantodefi/xmtpauth/xmtpgit clone --depth 1 https://github.com/tantodefi/xmtpauthWrote 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/tantodefi/xmtpauth/xmtp)<a href="https://agentmods.dev/rules/tantodefi/xmtpauth/xmtp"><img src="https://agentmods.dev/badge/rules/tantodefi/xmtpauth/xmtp.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 | $0.06601 | $0.06601 |
| Opus 5 | $0.03300 | $0.03300 |
| Sonnet 5 | $0.01320 | $0.01320 |
| Haiku 4.5 | $0.00660 | $0.00660 |
Grade A, and why
xmtp 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 4d 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 — 943 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing XMTP Agents
You're an expert in writing TypeScript with Node.js. Generate high-quality XMTP Agents that adhere to the following best practices:
Guidelines
-
Use modern TypeScript patterns and ESM modules. All examples should be structured as ES modules with
importstatements rather than CommonJSrequire(). -
Use the XMTP node-sdk version "2.0.2" or newer, which offers enhanced functionality including group conversations.
-
Only import from @xmtp/node-sdk for XMTP functionality. Do not import from any other XMTP-related packages or URLs. Specifically:
- Never use the deprecated @xmtp/xmtp-js library, which has been completely replaced by @xmtp/node-sdk
- Always import directly from @xmtp/node-sdk as shown below:
// CORRECT: import { Client, type Conversation, type XmtpEnv } from "@xmtp/node-sdk"; // INCORRECT - DEPRECATED: import { Client } from "@xmtp/xmtp-js"; import { XmtpClient } from "some-other-package"; -
Follow the consistent pattern for initializing XMTP clients:
const signer = createSigner(WALLET_KEY); const encryptionKey = getEncryptionKeyFromHex(ENCRYPTION_KEY); const client = await Client.create(signer, { dbEncryptionKey: encryptionKey, env: XMTP_ENV as XmtpEnv, }); -
Use proper environment variable validation at the start of each application. Check for required environment variables and show descriptive errors if missing.
-
Never use the concept of "topic" when working with XMTP. The current SDK doesn't use topics for message organization - work directly with conversations, groups, and DMs instead.
-
Handle both Group and DM conversations properly. The
GroupandDmclasses extend theConversationclass and provide specific functionality:if (conversation instanceof Group) { // Group-specific functionality like group.name or group.addMembers } else if (conversation instanceof Dm) { // DM-specific functionality like conversation.peerInboxId }
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.
- 4d ago First seen · 943 lines · 6,601 tokens per session scan A a5cc8be9b3f0
xmtp is a cursor rule published in the GitHub repository tantodefi/xmtpauth (3 stars, last pushed 11mo ago), licensed MIT. It adds 6,601 tokens to every session, about $0.0330 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
solana-integration-constraints
Constraints and requirements for Solana integration with MetaMask Connect — wallet adapter config, CAIP-2 IDs, network support per platform, RPC routing, and platform limitations.
zama-protocol-zama-solidity--setups-foundry
Detailed reference for foundry (zama-solidity skill).
cardano-mcp
These rules complement our main development collaboration rules, focusing specifically on the Model Context Protocol (MCP) server project with TypeScript. This project serves as a specialized RAG (Retrieval-Augmented Generation) gateway to existing Cardano resources, documentation, and tools to assist with dApp…
stacks-development
Guidelines for Stacks blockchain development.
solana_monitoring_analytics
Solana blockchain development, production monitoring, analytics, and observability.
solana_core_architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Entry Point │ │ Instruction │ │ Account │ │ lib.rs │───▶│ Processing │───▶│ Validation │ │ │ │ │ │ │ │ - entrypoint! │ │ - Route dispatch │ │ - Owner checks │ │ - processinst │ │ - Deserialize │ │ - Data validate │.