Developers · Agents

Make agents build the one-call path first.

The best agent path is short: load the skill, call offramp(walletClient, params), verify delegation, then add Peerlytics route data or explorer reads only if the product needs them.

Open the agent skillRead llms-full.txt
01

Agent context pack

ResourceUse
skills/usdctofiat.mdDrop-in skill with SDK rules, platforms, OTC, and examples
llms.txtShort machine-readable product and route summary
llms-full.txtFull machine reference with contracts, pricing, guides, and answers
OFFRAMP_DEVELOPER_RESOURCESTyped SDK export with links, delegation config, upstreamSourceTruths, and playbooks
OFFRAMP_INTEGRATION_CHECKLISTTyped integration-doctor checks for delegation, duplicate prevention, and extension recovery
getOfframpAgentPrompt(profile)Copyable prompt builder for agent-built integrations
Starters repoWorking Next.js, Vite, Telegram-bot, and script examples
02

Prompt sequence

  1. 01Tell the agent to read the skill and llms.txt before planning.
  2. 02Tell it to ship the one-call offramp(walletClient, params) path before adding data-plane features.
  3. 03Pick a profile: app, bot, agent, private-otc, or peerlytics.
  4. 04Ask it to scaffold from create-offramp-app or the starters repo when possible.
  5. 05Require it to verify every created deposit delegates to the Delegate rate manager.
  6. 06If it adds Peerlytics, require planRoutes() before raw orderbook reads.
03

What agents must not invent

  • Do not invent a sandbox; the SDK targets Base mainnet.
  • Do not remove delegation; the SDK's deposit path must delegate to the Delegate vault.
  • Do not treat fiat as SDK-controlled. Fiat moves directly between buyer and seller.
  • Do not fabricate proof payloads, credential fields, or payment-method hashes; check upstreamSourceTruths first.

Keep exploring

Offramp SDKPeerlytics APIDeveloper hub

Common questions

What should an agent read first?

Start with https://usdctofiat.xyz/skills/usdctofiat.md, then llms.txt or llms-full.txt depending on how much context the model can hold.

Can agents discover this from the package?

Yes. Import OFFRAMP_DEVELOPER_RESOURCES, OFFRAMP_INTEGRATION_CHECKLIST, read OFFRAMP_DEVELOPER_RESOURCES.upstreamSourceTruths, call getOfframpDeveloperResources(profile), or call getOfframpAgentPrompt(profile) from @usdctofiat/offramp.