A payment-management guide for MoneyClaw, a service that lets agents inspect a prepaid wallet and prepare user-authorized payments. Payment tasks can require approval before money is spent.

Use it to inspect wallet status, create payment tasks, check account messages, and continue approved payments through MoneyClaw.

It keeps payment actions bounded, reviewable, and tied to explicit user authorization.

moneyclaw — Skill for Codex by elvismusli

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 elvismusli/moneyclaw --skill moneyclaw-skill

Clone the repo

git clone --depth 1 https://github.com/elvismusli/moneyclaw

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/elvismusli/moneyclaw/moneyclaw-skill/github.svg)](https://agentmods.dev/skills/elvismusli/moneyclaw/moneyclaw-skill)

Your own site

<a href="https://agentmods.dev/skills/elvismusli/moneyclaw/moneyclaw-skill"><img src="https://agentmods.dev/badge/skills/elvismusli/moneyclaw/moneyclaw-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/elvismusli/moneyclaw/moneyclaw-skill"><img src="https://agentmods.dev/badge/skills/elvismusli/moneyclaw/moneyclaw-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,762 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.01762
Opus 5.5	$0.00018	$0.00705
Sonnet 5.5	$0.00009	$0.00352
Haiku 4.5	$0.00005	$0.00176

Measured 2mo ago against content hash 2b0f70d7a274, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

moneyclaw 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 2mo 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.

curl -H "Authorization: Bearer $MONEYCLAW_API_KEY" \

Origin

This is a copy

100% identical to moneyclaw — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

moneyclaw-skill/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MoneyClaw

MoneyClaw helps OpenClaw agents inspect prepaid payment state, create auditable payment tasks, and continue explicitly requested payment steps.

Primary use case: buyer-side payments for OpenClaw agents.

Authentication

This skill requires one MoneyClaw API key.

Authorization: Bearer $MONEYCLAW_API_KEY

Base URL: https://moneyclaw.ai/api

Trust Model

MoneyClaw is designed for real, user-authorized agent payments.

use prepaid balances to keep risk bounded
use payment intents as the main auditable execution surface
keep account inbox state inspectable for receipts and account messages
let the user approve the payment step before money moves

Approval Model

Default to dashboard approval unless the account has explicitly enabled agent auto-approval.

MoneyClaw accounts expose an account-level agentAutoApproveEnabled flag through GET /api/me.
When that flag is off, API-key-created payment tasks wait for dashboard approval before spending.
When that flag is on, API-key-created payment tasks can be auto-approved within the merchant and amount scope of the task.
Do not assume agent auto-approval is enabled unless the account state confirms it.

Safety Boundaries

Only use MoneyClaw for purchases or payment flows explicitly requested by the user. If the account is not clearly configured for agent auto-approval and the user has not explicitly asked for the next payment step, stop and ask.
Only use wallet, card, and billing data returned by the user's own MoneyClaw account.
Respect merchant, issuer, card-network, and verification controls.
Treat fraud checks, KYC, sanctions, geography rules, merchant restrictions, issuer declines, and other payment controls as hard boundaries.
Never fabricate billing identity, cardholder data, addresses, names, phone numbers, or verification information.
If a transaction fails, looks suspicious, or produces conflicting signals, stop and inspect transaction state before retrying.
Prefer prepaid, bounded-risk flows by default.
Never invoke this skill automatically from a shopping, billing, or checkout page. Use it only after an explicit user request to use MoneyClaw.

Read the full file on GitHub · 178 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.

2mo ago First seen · 178 lines · 45 tokens per session scan A 2b0f70d7a274

Subscribe to this mod's changes

moneyclaw is a skill published in the GitHub repository elvismusli/moneyclaw (8 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 1,762 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to moneyclaw, differing in 0 lines, and is treated as a copy.

Finance and fintech agent-commerce ai-agents fintech openclaw otp payments

moneyclaw next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
moneyclawelvismusli/moneyclaw	Skill	8	7mo ago	MIT	A	45	Codex
daily-deep-briefKCNyu/clawock	Skill	23	today	MIT	A	163	Claude Code, Codex
hk-stock-analysisKCNyu/clawock	Skill	23	today	MIT	A	126	Claude Code, Codex
us-stock-analysisKCNyu/clawock	Skill	23	today	MIT	A	97	Claude Code, Codex
portfolio-swarm-reviewKCNyu/clawock	Skill	23	today	MIT	A	90	Claude Code, Codex
investment-decisionKCNyu/clawock	Skill	23	today	MIT	A	62	Claude Code, Codex
entry-gateKCNyu/clawock	Skill	23	today	MIT	A	109	Claude Code, Codex

moneyclaw