fluxa-agent-wallet

fluxa-agent-wallet is a skill for Claude Code, Codex from FluxA-Agent-Payment/FluxA-AI-Wallet-MCP. It costs 203 tokens per session (5,101 once invoked), scanned A, original, Apache-2.0.

A wallet skill that lets an AI agent use a user's wallet within an approved scope. It supports payments, USDC transfers, payment links, agent transfers, and virtual cards.

In plain words
What is it for?
Making x402 payments, transferring USDC, receiving money through payment links, discovering paid APIs, and using prepaid virtual cards.
Why use it?
It provides a controlled way for an agent to handle payment-related actions while requiring confirmation before spending or adding funds.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; mentions Claude Code; built for openclaw.

Good fit Making x402 payments, transferring USDC, receiving money through payment links, discovering paid APIs, and using prepaid virtual cards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet
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 FluxA-Agent-Payment/FluxA-AI-Wallet-MCP --skill fluxa-agent-wallet
Clone the repo
git clone --depth 1 https://github.com/FluxA-Agent-Payment/FluxA-AI-Wallet-MCP

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 fluxa-agent-wallet

README.md
[![agentmods](https://agentmods.dev/badge/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet/github.svg)](https://agentmods.dev/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet)
Your own site
<a href="https://agentmods.dev/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet"><img src="https://agentmods.dev/badge/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet/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 fluxa-agent-wallet

Your own site · 80×15
<a href="https://agentmods.dev/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet"><img src="https://agentmods.dev/badge/skills/fluxa-agent-payment/fluxa-ai-wallet-mcp/fluxa-agent-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00203 $0.05101
Opus 5 $0.00102 $0.02550
Sonnet 5 $0.00041 $0.01020
Haiku 4.5 $0.00020 $0.00510

Measured 5d ago against content hash 2de780a64eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fluxa-agent-wallet scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

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

1. curl -s <x402_url> → Get full payload from JSON or response header
skills/fluxa-agent-wallet/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FluxA Agent Wallet

Skill version: 0.5.0 | CLI version: @fluxa-pay/[email protected]MUST install or update to the latest CLI version before use.

FluxA Agent Wallet is a co-wallet that allows AI agents to securely use a user’s wallet, enabling them to perform payment-related actions within the user’s approved scope. Capabilities include x402 payments, USDC transfers, agent-to-agent transfers, payment links for receiving payments, prepaid virtual cards, AI social gifting, discovering and calling x402 resources (one-shot APIs), and using payment-related skills (one-shot skills). Use this tool when the user the user asks to perform any of these payment-related actions.

Hard Rules

  • Confirm every topup or spend with the user before initiating it. Present the cost first and get an explicit choice. Each charge must be a known, deliberate spend.
  • Never write payment code. No x402 signing or mandate logic in app code. Agents use the wallet CLI; apps use API keys.
  • Report costs honestly. Surface X-LLM-Cost-Credits after FluxA Monetize model calls; a negative balance is unsettled debt (usage consumed but not yet paid). Say so plainly.

Setup

Step 1 — Install the CLI

npm install -g @fluxa-pay/[email protected]

Then run commands directly:

fluxa-wallet <command> [options]

Step 2 — Init Wallet

Before any operation, the agent must have an Agent ID.

First, check if the agent is already initialized:

fluxa-wallet status

If configured is true, the agent is already initialized — skip the init step. If init has already been run, running it again will be ignored.

If not initialized, register once:

fluxa-wallet init \
  --name “eg. My AI Agent” \
  --client “eg. OpenClaw v1.0.0”

The CLI will save Agent ID credential in ~/.fluxa-ai-wallet-mcp/config.json.

Link to user’s wallet: After init, check if the agent is already linked:

fluxa-wallet check-wallet

Read the full file on GitHub · 340 lines

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. 5d ago Changed · +5 lines 2de780a64eef
  2. 12d ago First seen · 335 lines · 203 tokens per session scan A 231bc53e825f

Subscribe to this mod's changes

fluxa-agent-wallet is a skill published in the GitHub repository FluxA-Agent-Payment/FluxA-AI-Wallet-MCP (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 203 tokens to every session and 5,101 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.