solana-developer-platform: Skill for Claude Code

.agents/skills/integrate-offramp/SKILL.md

integrate-offramp is a skill for Claude Code, Codex from solana-foundation/solana-developer-platform. It costs 44 tokens per session (1,006 once invoked), scanned A, original, MIT.

A development guide for adding an off-ramp provider, which lets a user exchange cryptocurrency in a wallet for regular money paid to a bank or payout account.

In plain words
What is it for?
Use it when adding or updating a service that converts crypto to fiat currency.
Why use it?
It shows how to create the provider's quote and connect it to the API, database, wallet rules, and dashboard.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is solana-foundation/solana-developer-platform's own configuration. It tells Claude Code and Codex how to work on solana-developer-platform itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything solana-developer-platform configures →

Reuse

Borrowing it

Nothing to install: this file belongs to solana-foundation/solana-developer-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/solana-foundation/solana-developer-platform/main/.agents/skills/integrate-offramp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/solana-foundation/solana-developer-platform

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for integrate-offramp

README.md
[![agentmods](https://agentmods.dev/badge/skills/solana-foundation/solana-developer-platform/integrate-offramp.svg)](https://agentmods.dev/skills/solana-foundation/solana-developer-platform/integrate-offramp)
Your own site
<a href="https://agentmods.dev/skills/solana-foundation/solana-developer-platform/integrate-offramp"><img src="https://agentmods.dev/badge/skills/solana-foundation/solana-developer-platform/integrate-offramp.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01006
Opus 5 $0.00022 $0.00503
Sonnet 5 $0.00009 $0.00201
Haiku 4.5 $0.00004 $0.00101

Measured 4d ago against content hash 7dd28456f2f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

integrate-offramp 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 4d 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.

.agents/skills/integrate-offramp/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate off-ramp

Off-ramp = a counterparty sells crypto from an SDP wallet for fiat paid to a payout account. Implement createOfframpQuote and add a branch to the API dispatch. There is no executeOfframp method in the current provider contract.

createOfframpQuote is required on RampProvider (unlike createOnrampQuote, which is optional) — even a provider that doesn't support off-ramp must implement it; the dispatch case for that provider can throw instead of calling it (several registered providers do exactly that today rather than reaching the client method).

Choose the closest package client under packages/sdp-payments/src/ramps/providers/ by delivery mode: manual instructions with payout provisioning, a hosted widget, or a session widget.

Contract

Read the current RampOfframpQuoteInput from packages/sdp-payments/src/ramps/types.ts. The handler resolves the SDP wallet address, counterparty, provider customer/account ids, and any caller-defined transfer reference before calling the package client.

Output PaymentRampQuote is closed by provider and deliveryMode; add the provider quote/instruction arm in packages/sdp-types/src/payments.ts as described by integrate-onramp.

Two off-ramp-specific resolutions (handler-side)

  1. Source wallet. The shared policy extraction resolves sourceWallet to an SDP wallet/address and gates the value-moving operation through policyGate. Do not accept a provider account id in place of the SDP source wallet.

  2. Payout account. The fiat needs a destination bank account, and a counterparty may hold several active accounts per corridor (per rail). The quote request takes an optional providerAccountId (the counterparty_provider_accounts row id): when present, the handler resolves it parent-scoped and rejects a mismatched corridor; when absent, it lists the corridor's active rows and applies the provider's selection helper. Accounts are JIT-created by the requirements advance flow — the raw bank details are sent to the provider and never stored. Missing/inactive account throws counterpartyNotProvisioned; the transfer records the chosen row id as payoutProviderAccountId in its provider data.

Read the full file on GitHub · 50 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 4d ago Changed · -1 lines 7dd28456f2f1
  2. 8d ago First seen · 51 lines · 44 tokens per session scan A 31e693d6b986

Subscribe to this mod's changes

integrate-offramp is a skill published in the GitHub repository solana-foundation/solana-developer-platform (52 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,006 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 2026-08-30.