Jump to related tools in the same category or review the original source on GitHub.

Health & Fitness @josephrp Updated 2/9/2026

๐Ÿ“ˆ Autonomous Agent OpenClaw Plugin & Skill | ClawHub

Looking to integrate Autonomous Agent into your AI workflows? This free OpenClaw plugin from ClawHub helps you automate health & fitness tasks instantly, without having to write custom tools from scratch.

What this skill does

CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 โ†’ pay โ†’ retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.

Install

npx clawhub@latest install autonomous-agent

Full SKILL.md

Open original
Metadata table.
namedescription
autonomous-agentCornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 โ†’ pay โ†’ retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.

SKILL.md content below is scrollable.

CornerStone MCP x402 Skill (for Agents)

This skill gives you (the agent) a set of tools to: create and manage Aptos and EVM wallets, check balances, and call x402-paid MCP tools (stock prediction, backtest, bank linking, agent/borrower scores). Payment is automatic โ€” when a paid tool returns 402, the skill signs, verifies, settles, and retries transparently. You just call the tool; the result comes back.


Quick-start workflow

Follow this sequence on first use, then skip to the tool you need:

  1. Check wallets โ†’ call get_wallet_addresses (no args).
  2. If empty โ†’ call create_aptos_wallet then create_evm_wallet.
  3. Fund โ†’ call credit_aptos_wallet (Aptos faucet) and fund_evm_wallet (EVM faucet instructions).
  4. Tell the user to whitelist the returned addresses at https://arnstein.ch/flow.html.
  5. Check balance โ†’ call balance_aptos (must have USDC for predictions/backtests) and/or balance_evm (must have ETH for bank linking).
  6. Use paid tools โ†’ run_prediction, run_backtest, link_bank_account, or score tools.

Important: Paid tools will fail with a wallet/whitelist error if the address has not been funded and whitelisted. Always verify wallets and balances first.


Tool reference

Wallet management tools (local)

get_wallet_addresses

  • Args: none
  • Returns: { aptos: [{ address, network }], evm: [{ address, network }] } โ€” may be empty arrays.
  • When to use: Always call first before any wallet or paid tool action. Determines what exists.
  • Decision: If both arrays are empty โ†’ create wallets. If only one is empty โ†’ create the missing one. If both have entries โ†’ proceed to balance check or paid tools.

create_aptos_wallet

  • Args: { force?: boolean, network?: "testnet" | "mainnet" } โ€” defaults: force=false, network=testnet.
  • Returns: { success, address, network, message } or { success: false, message, addresses } if wallet exists and force=false.
  • When to use: When get_wallet_addresses returns empty aptos array, or user requests a new wallet.
  • Error handling: If success: false and wallet already exists, either use the existing wallet or retry with force: true to add another.

create_evm_wallet

  • Args: { force?: boolean, network?: "testnet" | "mainnet" } โ€” defaults: force=false, network=testnet.
  • Returns: { success, address, network, message } or { success: false, message, addresses }.
  • Same pattern as create_aptos_wallet.

credit_aptos_wallet

  • Args: { amount_octas?: number } โ€” default 100,000,000 (= 1 APT).
  • Returns on devnet: { success: true, address } (programmatic faucet funded).
  • Returns on testnet: { success: true, address, faucet_url } (instructions only; no programmatic faucet).
  • Prerequisite: Aptos wallet must exist (create_aptos_wallet first).
  • Note: Funded APT is for gas; tools pay in USDC (~6ยข). The user may need to acquire testnet USDC separately.

fund_evm_wallet

  • Args: none
  • Returns: { success: true, address, faucet_url, message } (manual funding instructions).
  • Prerequisite: EVM wallet must exist (create_evm_wallet first).
  • Note: Returns a Base Sepolia faucet URL. The user must fund manually; there is no programmatic faucet.

Balance tools (local)

balance_aptos

  • Args: none
  • Returns: { address, balances: { usdc, apt } } or { error }.
  • When to use: Before calling run_prediction, run_backtest, or score tools to confirm sufficient USDC.

balance_evm

  • Args: { chain?: string } โ€” default "base". Supported: base, baseSepolia, ethereum, polygon, arbitrum, optimism.
  • Returns: { address, chain, balance, symbol } or { error }.
  • When to use: Before calling link_bank_account to confirm sufficient ETH on Base Sepolia.
  • Note: For testnet tools, use chain: "baseSepolia".

Paid MCP tools (x402 โ€” payment handled automatically)

All paid tools accept both Aptos and EVM payment. The skill picks the best option or follows PREFERRED_PAYMENT_ORDER. You never see 402 errors โ€” just call the tool and get the result or an error message.

run_prediction

  • Args: { symbol: string, horizon?: number } โ€” symbol is a stock ticker (e.g. "AAPL"), horizon is days (default 30).
  • Returns: Prediction result object (forecast data, confidence intervals, etc.) or { error }.
  • Cost: ~6ยข USDC (Aptos or EVM).
  • Prerequisite: Funded + whitelisted Aptos or EVM wallet.
  • Example call: run_prediction({ symbol: "AAPL", horizon: 30 })

run_backtest

  • Args: { symbol: string, startDate?: string, endDate?: string, strategy?: string } โ€” dates in "YYYY-MM-DD", strategy defaults to "chronos".
  • Returns: Backtest result (returns, drawdown, sharpe, etc.) or { error }.
  • Cost: ~6ยข USDC.
  • Example call: run_backtest({ symbol: "TSLA", startDate: "2024-01-01", endDate: "2024-12-31", strategy: "chronos" })

link_bank_account

  • Args: none
  • Returns: { link_token } or account ID for Plaid bank linking, or { error }.
  • Cost: ~5ยข (EVM/Base).
  • Prerequisite: Funded + whitelisted EVM wallet (Base Sepolia for testnet).

get_agent_reputation_score

  • Args: { agent_address?: string, payer_wallet?: string } โ€” both optional; uses the configured wallet if omitted.
  • Returns: { reputation_score: number } (e.g. 100) or 403 if not allowlisted, or { error }.
  • Cost: ~6ยข via x402, or free with lender credits (pass payer_wallet).

get_borrower_score

  • Args: { agent_address?: string, payer_wallet?: string } โ€” same pattern.
  • Returns: { score: number } (100 base; higher with bank linked) or { error }.
  • Cost: ~6ยข via x402, or free with lender credits.

get_agent_reputation_score_by_email

  • Args: { email: string, payer_wallet?: string } โ€” resolves email to allowlisted agent.
  • Returns: { reputation_score: number } or { error }.
  • Prerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee.

get_borrower_score_by_email

  • Args: { email: string, payer_wallet?: string } โ€” same pattern.
  • Returns: { score: number } or { error }.
  • Prerequisite: SCORE_BY_EMAIL_ENABLED must be set on the server. Higher fee.

Decision tree for common tasks

"Run a prediction for X"

get_wallet_addresses
  โ†’ aptos empty? โ†’ create_aptos_wallet โ†’ credit_aptos_wallet โ†’ tell user to whitelist
  โ†’ aptos exists? โ†’ balance_aptos
    โ†’ has USDC? โ†’ run_prediction({ symbol: "X", horizon: 30 })
    โ†’ no USDC? โ†’ tell user to fund USDC, provide address

"Link a bank account"

get_wallet_addresses
  โ†’ evm empty? โ†’ create_evm_wallet โ†’ fund_evm_wallet โ†’ tell user to whitelist
  โ†’ evm exists? โ†’ balance_evm({ chain: "baseSepolia" })
    โ†’ has ETH? โ†’ link_bank_account
    โ†’ no ETH? โ†’ fund_evm_wallet (returns faucet URL)

"Get my scores"

get_wallet_addresses
  โ†’ has aptos or evm? โ†’ get_agent_reputation_score + get_borrower_score
  โ†’ neither? โ†’ create wallets first, whitelist, then query

Error handling

Error pattern Meaning What to do
"No Aptos wallet" Wallet file missing Call create_aptos_wallet
"No EVM wallet" Wallet file missing Call create_evm_wallet
"already exist. Use force: true" Wallet exists, not overwriting Use existing wallet, or pass force: true to add another
"Payment verification failed" Insufficient funds or wrong asset Check balance; tell user to fund the wallet
"No Aptos wallet configured" / "No EVM wallet configured" Paid tool needs wallet that doesn't exist Create the missing wallet type
"Unsupported chain" Invalid chain name for balance_evm Use one of: base, baseSepolia, ethereum, polygon, arbitrum, optimism
"timed out after 300s" MCP call took too long Retry once; the server may be under load
"403" or "not allowlisted" Wallet not whitelisted Tell user to whitelist address at https://arnstein.ch/flow.html

Setup (for the human installing this skill)

  1. Install: npm install from repo root. Copy .env.example to .env.
  2. Configure: Set wallet paths (APTOS_WALLET_PATH, EVM_WALLET_PATH or EVM_PRIVATE_KEY).
  3. Wallets: Create via tools (create_aptos_wallet, create_evm_wallet) or CLI (node src/setup-aptos.js, node src/setup.js). Fund and whitelist all addresses at https://arnstein.ch/flow.html.

CLI commands (from repo root)

Task Command
Generate Aptos wallet npm run setup:aptos
Generate EVM wallet npm run setup
Show addresses for whitelist npm run addresses
Credit Aptos (devnet) npm run credit:aptos (set APTOS_FAUCET_NETWORK=devnet)
EVM balance npm run balance -- <chain>
Transfer ETH/tokens npm run transfer -- <chain> <to> <amount> [tokenAddress]
Swap tokens (Odos) npm run swap -- <chain> <fromToken> <toToken> <amount>
Run skill demo npx cornerstone-agent "Run a 30-day prediction for AAPL"
Attest Aptos wallet npm run attest:aptos
Attest EVM wallet npm run attest:evm

Source: FinTechTonic/autonomous-agent

Original Repository URL: https://github.com/openclaw/skills/blob/main/skills/josephrp/autonomous-agent
Latest commit: https://github.com/openclaw/skills/commit/43cc8ef94021943917b2a35d97fa201e160fd71b

Related skills

If this matches your use case, these are close alternatives in the same category.