Recipes
Quick, self-contained solutions for specific tasks. Each recipe assumes you have an active agent with an SDK key. For initial setup, see Quickstart.Agent Frameworks
Both skill flavors below rely onconto-check.sh, which in turn requires curl, jq, and python3
on PATH. curl and python3 ship with macOS and most Linux distros; install jq via your
package manager. python3 powers the localhost OAuth callback used by conto-check.sh setup.
Install the OpenClaw Skill
Install the Hermes Skill
Setup
Connect an Agent via API
conto_...) for this call.
Generate an SDK Key via API
Provision a Sponge Wallet
Sponge custody uses the@paysponge/sdk under the hood. Set SPONGE_API_KEY (and SPONGE_MASTER_KEY for fleet management) in your environment.
Link a Wallet to an Agent
Check Agent Setup
Verify the agent is correctly configured with wallets and policies:Payments
Request and Execute a Payment
Two calls: request (policy check) → execute (onchain transfer).Pay an AgentScore-Gated Merchant
If the merchant is AgentScore-native, include the merchant compliance policy in the request. Conto will returnVERIFICATION_REQUIRED with a verification URL when the operator identity needs a
step-up before settlement.
VERIFICATION_REQUIRED, direct the human to verification.verifyUrl.
Once the session completes, Conto re-runs policy evaluation and auto-executes if the original call
used autoExecute: true.
Accept Agent Payments Through a Merchant Gate
Create a hosted gate for your merchant org:merchant:purchase scope:
403 with
AgentScore verify_url / poll_url / poll_secret fields when identity verification is still
required.
Check Transaction Status
PENDING, CONFIRMING, CONFIRMED, FAILED, or REJECTED.
List Recent Transactions
Pre-Authorize an x402 Payment
"authorized": true with wallet details, or "authorized": false with violation reasons.
Record an x402 Transaction
After the x402 payment executes onchain:Check x402 Budget
?sessionId=... if you want the budget view scoped to a single x402 session.
Approve and Confirm an External Wallet Payment
Use this flow when your agent holds its own keys and Conto should only authorize the spend.Policies
Limit Agent to $50/Day
Require Approval Above $100
Block Payments Outside Business Hours
Allowlist Specific Recipients
Cap x402 API Spending
Restrict to Allowed x402 Services
Cap MPP Session Deposits
Restrict MPP to Allowed Services
Approvals & Trust
Look Up Trust for a Counterparty Address
network:read scope. Returns global trust information, relationship-specific trust
data, transaction history, and any network flags.
Require Approval for Large Payments and Use Slack for Review
The fastest production pattern is:- Create an approval threshold rule:
- Configure a Slack approval channel:
MPP Payments
Pre-Authorize an MPP Session
"authorized": true with wallet details, or "authorized": false with violation reasons.
Record an MPP Settlement
After closing a session, record the settled amount:Check MPP Budget
?sessionId=... if you want the budget response scoped to one MPP session.
List MPP Services Used
Monitoring
Get Agent Spending Summary
Get Wallet Balance
List Active Alerts
TypeScript SDK Equivalents
The recipes above use curl. Here are the payment operations in TypeScript using the SDK:The
Conto class provides conto.payments for agent payment operations. For admin operations
(agents, wallets, policies) use ContoAdmin — see the Admin SDK. For x402, MPP,
transaction listing, and wallet queries, use the REST API endpoints shown in the curl recipes
above.Related
Choose Integration
SDK vs Agent Skills vs x402 vs MPP
Quickstart
Full setup walkthrough
x402 Payments
Pay for APIs with x402
MPP Sessions
Session-based micropayments
Approval Workflows
Add review and escalation controls
Trust Scoring
Use counterparty trust as a control surface