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/SELAT-AI/selat-openclaw-skillsnpx agentmods add skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamaskWrote 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/skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamask)<a href="https://agentmods.dev/skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamask"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamask/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/skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamask"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-openclaw-skills/selat-capabilities-for-metamask.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 | $0.00225 | $0.02229 |
| Opus 5 | $0.00112 | $0.01115 |
| Sonnet 5 | $0.00045 | $0.00446 |
| Haiku 4.5 | $0.00022 | $0.00223 |
Grade A, and why
selat-capabilities-for-metamask 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 12d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
selat-capabilities-for-metamask
SELAT's capability layer, wired to a MetaMask Agent Wallet. When a task needs tool use beyond the agent's native abilities — web search, scraping, data enrichment, real-time market data, media generation, on-chain reads — this skill turns "I can't do that" into a purchasable capability: discover paid APIs by intent across SELAT's federated catalog, buy them on any rail SELAT routes (including Gateway-batched x402 and MPP, which the wallet's native x402 payer cannot sign), fund a Circle Gateway purchasing budget gaslessly, run declarative skill manifests, and report spend. Side-effecting — it spends real money once the user opts in; discovery and probing are free.
Where it shines for MetaMask Agent Wallet users: decision support for trading — perpetuals and tokenized stocks. The catalog carries the reads a trading decision leans on: perp funding rates and venue context, prediction market candles, equity quotes and technical indicators for a tokenized stock's underlying, earnings and news sentiment, social chatter, and macro regime data. This skill buys research data only — it never places, cancels, or manages orders, and its output is never financial advice; the decision and any trade stay with the user, on their own venue.
It wraps the selat-purchasing skill from
SELAT-AI/selat-metamask-skills.
How this wrapper differs from the others in this repo: it does not
install the selat CLI or any SELAT plugin, and it does not wrap a
selat-skills recipe. Its engine is the MetaMask Agent Wallet CLI (mm)
plus the upstream skill's Python scripts (standard library only — no
third-party packages). SELAT is used keylessly as the catalog and payment
router; custody stays entirely with the MetaMask wallet.
Cost — read this first
- Every purchase is real USDC from the user's own self-custodial MetaMask
Agent Wallet and its Circle Gateway balance. SELAT never holds keys or
funds; every signature and on-chain action goes through the
mmCLI — the upstream scripts never touch key material. - Prices live in the live 402 quotes, not here. Probe first (Step 1 — free, nothing signed), show the user the quoted prices, and get their OK. A refused or expired quote charges nothing.
- It's a menu, not a pipeline. Discovery, funding, paying, manifests, and spend reports are independent operations — run only what the request needs.
- Follow the upstream confirmation pattern: purchases above the session threshold are always shown for approval with amount, merchant, and network; a manifest is many purchases, so always dry-run it and show the quoted total before executing.
- The Gateway deposit is the purchasing cap — nothing this skill does can spend more than the user deposited plus what the wallet's own policy allows.
- Never ask for, paste, or handle a private key. Wallet auth is the
mmCLI's sign-in flow.
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.
- 12d ago First seen · 172 lines · 225 tokens per session scan A 8f69d5a910ae
selat-capabilities-for-metamask is a skill published in the GitHub repository SELAT-AI/selat-openclaw-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 225 tokens to every session and 2,229 once invoked, about $0.0011 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 skills, from other repositories
wallet-desk-brief
Use this skill when the user wants a who-is-this-wallet brief on one EVM address — e.g. "who is 0x...", "label this wallet", "wallet desk brief on 0x...", "what tokens does this address hold and who owns it", "Arkham + holdings read of 0x...". Pins Alchemy tokens-by-address (x402 via Circle Gateway; verify prints…
okx-agent-payments-protocol
Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channelid, opening / closing / topping up / settling / refunding a…
jupiter-lend
Interact with Jupiter Lend Protocol. Read-only SDK (@jup-ag/lend-read) for querying liquidity pools, lending markets (jlTokens), and vaults. Write SDK (@jup-ag/lend) for lending (deposit/withdraw) and vault operations (deposit collateral, borrow, repay, manage positions).
okx-dapp-discovery
Plugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI…
lifi
LI.FI REST API for cross-chain and same-chain token swaps, bridging, DeFi deposits (Composer), yield discovery (Earn), and intent-based execution (Intents). USE THIS SKILL WHEN USER WANTS TO: Swap tokens between different blockchains (e.g., "swap USDC on Ethereum to ETH on Arbitrum") Bridge tokens to another chain…
x402-erc7710
Design and implement demos combining x402 HTTP payments with ERC-7710 smart contract delegations and ERC-7715 wallet permission requests for subscriptions, bounded agent budgets, recurring spend, pay-per-use APIs, and agentic commerce.