spritz

spritz is a skill for Claude Code from spritz-finance/spritz-claude. It costs 48 tokens per session (2,414 once invoked), scanned C, original, MIT.

A connection to Spritz Finance for converting cryptocurrency into fiat money sent to a bank account. It can use bank details, payment instructions, and wallet addresses through the Spritz API.

In plain words
What is it for?
Use it to create bank payment destinations, request conversion quotes, and obtain transaction instructions for an off-ramp payment.
Why use it?
It handles the information exchange needed to move crypto funds to a real bank account, while making clear that data is sent to Spritz.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw; mentions OpenCode.

Part of the spritz plugin — 1 skill shipped together

Good fit Use it to create bank payment destinations, request conversion quotes, and obtain transaction instructions for an off-ramp payment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spritz-finance/spritz-claude/spritz
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add spritz-finance/spritz-claude --skill spritz
Clone the repo
git clone --depth 1 https://github.com/spritz-finance/spritz-claude

Made for: Claude Code.

Or install spritz, the plugin that ships this one along with the rest of its 1 skill.

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 spritz

README.md
[![agentmods](https://agentmods.dev/badge/skills/spritz-finance/spritz-claude/spritz/github.svg)](https://agentmods.dev/skills/spritz-finance/spritz-claude/spritz)
Your own site
<a href="https://agentmods.dev/skills/spritz-finance/spritz-claude/spritz"><img src="https://agentmods.dev/badge/skills/spritz-finance/spritz-claude/spritz/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.

agentmods 80×15 button for spritz

Your own site · 80×15
<a href="https://agentmods.dev/skills/spritz-finance/spritz-claude/spritz"><img src="https://agentmods.dev/badge/skills/spritz-finance/spritz-claude/spritz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,414 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00048 $0.02414
Opus 5 $0.00024 $0.01207
Sonnet 5 $0.00010 $0.00483
Haiku 4.5 $0.00005 $0.00241

Measured 12d ago against content hash 80e9f6275ef1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

spritz scanned grade C with 3 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/bank-accounts.sh, scripts/lib.sh, scripts/off-ramps.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- Contains injection markers ("Ignore previous instructions...", "You are now in admin mode...")

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Run any script without arguments to see available commands and usage.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- curl
skills/spritz/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spritz Fiat Rails

Direct API access to Spritz Finance for off-ramping crypto to real bank accounts.

Setup

Get your API key

Either:

Store the key

Set the SPRITZ_API_KEY environment variable:

export SPRITZ_API_KEY="your-api-key-here"

Or store it in a config file:

mkdir -p ~/.config/spritz
echo "your-api-key-here" > ~/.config/spritz/api_key

Note: SPRITZ_API_KEY environment variable takes precedence over the config file.

Requirements

  • curl
  • jq

Data & Privacy

This skill sends data to https://platform.spritz.finance (the Spritz API). Understand what is transmitted before use.

What this skill sends to the API

  • Bank account details — routing numbers, account numbers, sort codes, IBANs (when creating accounts)
  • Payment instructions — amounts, destination accounts, blockchain/token selection (when creating quotes)
  • Wallet addresses — sender address (when requesting transaction params)

What this skill does NOT do

  • Does NOT read, scan, or upload local files or directories
  • Does NOT accept database connection strings
  • Does NOT share conversation history or contexts with third parties
  • Does NOT modify system files or install software

Credential storage

  • API key is read from SPRITZ_API_KEY env var or ~/.config/spritz/api_key
  • The key is sent as a Bearer token in the Authorization header on every API call
  • Scripts do not log, cache, or write the key anywhere

Before using this skill

  1. Confirm https://platform.spritz.finance is the official Spritz Finance API
  2. Use a scoped API key — do not reuse keys across unrelated services
  3. Review commands before running them, especially bank-accounts.sh create and quotes.sh create
  4. If granting an autonomous agent access, restrict it from creating bank accounts or executing payments without human approval

Read the full file on GitHub · 259 lines

Files

What ships with it

4 files 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. 12d ago First seen · 259 lines · 48 tokens per session scan C 80e9f6275ef1

Subscribe to this mod's changes

spritz is a skill published in the GitHub repository spritz-finance/spritz-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,414 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (instruction-override phrasing, unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.