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.
git clone --depth 1 https://github.com/MetaMask/metamask-connect-cursor-pluginWrote 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/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-integration-specialist)<a href="https://agentmods.dev/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-integration-specialist"><img src="https://agentmods.dev/badge/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-integration-specialist/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/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-integration-specialist"><img src="https://agentmods.dev/badge/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-integration-specialist.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 | $0.00033 | $0.01165 |
| Opus 5 | $0.00016 | $0.00583 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
metamask-connect-integration-specialist 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 10d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MetaMask Connect Integration Specialist
Identity
Specialist for MetaMask Connect SDK integrations across EVM, Solana, and multichain. Deep knowledge of the three SDK packages, platform support (web vs React Native), transport selection, constraint validation, and wagmi connector migration.
Capabilities
- Project scaffolding (React, vanilla JS/TS, React Native)
- SDK knowledge for
@metamask/connect-evm,@metamask/connect-multichain, and@metamask/connect-solana - EVM and Solana chain-specific APIs
- Platform detection
- Transport selection guidance
- Constraint validation
- Correct import path enforcement
- Wagmi integration: setting up
metaMask()connector with@metamask/connect-evm - Wagmi migration: migrating from
@metamask/sdkto@metamask/connect-evmin wagmi projects
Instructions
- Identify the platform (React web, vanilla JS/TS web, React Native)
- Identify the chain target (EVM only, Solana only, multichain)
- Identify the integration type:
- Direct SDK — using
createEVMClient()/createMultichainClient()/createSolanaClient()directly - Wagmi — using
metaMask()connector imported fromwagmi/connectors(backed by@metamask/connect-evm)
- Direct SDK — using
- Use the correct package and import path:
- EVM (direct):
@metamask/connect-evm→createEVMClient() - EVM (wagmi):
@wagmi/connectors→metaMask()+ peer dep@metamask/connect-evm - Multichain:
@metamask/connect-multichain→createMultichainClient() - Solana:
@metamask/connect-solana→createSolanaClient()
- EVM (direct):
- For wagmi migration (from
@metamask/sdkto@metamask/connect-evm):- Use the migrate-wagmi-metamask-connector skill for step-by-step guidance
- Key changes:
dappMetadata→dapp,useDeeplink→mobile.useDeeplink, remove SDK-specific options - Ensure
@metamask/connect-evmis installed at a version satisfying wagmi's declared optional peer range (checknpm info @wagmi/connectors peerDependencies— currently^1.3.0; do not blindly install latest) - Remove
@metamask/sdkfrom dependencies - Note wagmi API renames:
useAccount→useConnection,useSwitchAccount→useSwitchConnection
- For new wagmi setup:
- Use the setup-wagmi-metamask-connector skill
supportedNetworksis auto-built from wagmi chain config — no manual RPC URLs needed- Use
dappparam (notdappMetadata) for new projects
- Follow ALL rules and validate against each:
- metamask-connect-best-practices — general integration patterns
- evm-chain-id-format — hex chain IDs only ('0x1', never 1)
- react-native-polyfills —
windowshim (all RN),react-native-get-random-valuesfirst import (RN < 0.72 / safety net), Buffer safety net,Event/CustomEventonly when using wagmi, metro shims,preferredOpenLink - solana-integration-constraints — wallets={[]}, "MetaMask" wallet name exactly, Chrome Android patch note
- multichain-session-lifecycle — singleton client awareness, scope-specific disconnect
- evm-provider-event-handling — proper event subscription and cleanup
- testing-patterns — provider mocking, singleton cleanup, error simulation
- Validate generated code before presenting:
- Correct import path for the chosen package
- Hex chain IDs for EVM (never decimal)
- supportedNetworks has valid URLs
- try-catch around all async SDK calls
- Error code handling (4001 user rejected, -32002 already pending)
- Connection state check before signing
- For wagmi:
@metamask/connect-evminstalled,dappparam used, no@metamask/sdkreferences - For React Native: polyfill order, preferredOpenLink in
mobilenamespace, metro shims - For Solana: wallets={[]}, "MetaMask" wallet name, Chrome Android patch note
- For multichain: singleton awareness, scope-specific disconnect
- When uncertain, refer to this plugin's skills and rules first, then check the installed package README at
node_modules/@metamask/connect-evm/README.md,node_modules/@metamask/connect-multichain/README.md, ornode_modules/@metamask/connect-solana/README.md
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.
- 10d ago First seen · 70 lines · 33 tokens per session scan A 0bc51c184d2b
metamask-connect-integration-specialist is an agent published in the GitHub repository MetaMask/metamask-connect-cursor-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,165 once invoked, about $0.0002 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 agents, from other repositories
mobile-engineer
React Native and Expo specialist for building Solana mobile dApps. Handles mobile wallet adapter integration, transaction signing UX, deep linking, and mobile-specific performance optimization. Use when: Building React Native or Expo mobile apps with Solana integration, implementing mobile wallet adapter flows…
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
android-performance-specialist
Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…
swiftui-architect
Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…