robotmoney-cli

robotmoney-cli is a skill for Claude Code from robotmoney/robotmoney-skills-v0. It costs 192 tokens per session (2,688 once invoked), scanned A, original, MIT.

A command-line interface for checking and using the Robot Money stablecoin yield vault on the Base blockchain. It can report vault or user positions, prepare unsigned transactions, or execute transactions through a policy-controlled wallet.

In plain words
What is it for?
Use it to check APY, total value locked, caps, adapter details, balances, or position value, and to prepare or execute deposits, withdrawals, and redemptions on Base.
Why use it?
It provides one command interface for inspecting the vault and preparing or carrying out supported deposit, withdrawal, redemption, and basket transactions without the CLI holding private keys.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code; mentions Cursor.

Part of the robotmoney-cli plugin — 1 skill shipped together

Good fit Use it to check APY, total value locked, caps, adapter details, balances, or position value, and to prepare or execute deposits, withdrawals, and redemptions on Base.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/robotmoney/robotmoney-skills-v0/robotmoney-cli
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 robotmoney/robotmoney-skills-v0 --skill robotmoney-cli
Clone the repo
git clone --depth 1 https://github.com/robotmoney/robotmoney-skills-v0

Made for: Claude Code.

Or install robotmoney-cli, 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 robotmoney-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli/github.svg)](https://agentmods.dev/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli)
Your own site
<a href="https://agentmods.dev/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli"><img src="https://agentmods.dev/badge/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli/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 robotmoney-cli

Your own site · 80×15
<a href="https://agentmods.dev/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli"><img src="https://agentmods.dev/badge/skills/robotmoney/robotmoney-skills-v0/robotmoney-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 192 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,688 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.
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 $0.00192 $0.02688
Opus 5 $0.00096 $0.01344
Sonnet 5 $0.00038 $0.00538
Haiku 4.5 $0.00019 $0.00269

Measured 11d ago against content hash 127b12d64a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

robotmoney-cli 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 11d 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.

plugins/robotmoney-cli/skills/robotmoney-cli/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

robotmoney-cli

Experimental (pre-v1.0) — Command syntax, response schemas, and available operations may change. Always verify critical outputs independently.

Query the Robot Money stablecoin vault and either (a) build unsigned transactions for the caller to sign with their own wallet, or (b) sign and broadcast end-to-end via an Open Wallet Standard (OWS) wallet. All commands output JSON to stdout. The CLI never holds private keys — OWS does, under its policy-gated signing flow.

npx @robotmoney/cli <command> [options]

Chain: base only at launch. Every command requires --chain base.

Vault: 0x4f835c9f54bcf17daf9040f60cb72951ccbb49dd on Base — a multi-adapter ERC-4626 vault that splits USDC across Morpho Gauntlet USDC Prime, Aave V3, and Compound V3 by dynamic equal weight.

Basket leg: prepare-deposit and execute-deposit also buy a fixed 7-token agent basket (VIRTUAL, ROBOT, BNKR, JUNO, ZFI, GIZA, PEAQ) atomically via Uniswap UniversalRouter — 95% to vault, 5% across the basket by default. prepare-redeem / prepare-withdraw (and their execute-* siblings) can sell back any subset. See references/basket.md.

RPC: defaults to a built-in pool of 5 free Base endpoints with automatic fallback. Users don't need their own RPC URL. Pass --rpc-url <url> or set RPC_URL if you want to override.

Target users

This skill is for AI agents and autonomous machines — anything with a wallet (or the need for one) that wants diversified USDC yield. Works the same whether you're a Claude Code session, a Cursor agent, an autonomous trading bot, an IoT device, or a peaq-network machine. Not a retail-wallet UX — all output is JSON and meant to be parsed, not read by humans.

Deciding between prepare-* and execute-*

The CLI has two sign-time models:

  • prepare-* — returns unsigned calldata as JSON. Use when the caller has their own wallet/signer (Coinbase Smart Wallet, Safe, Fireblocks, hardware, etc.) and will sign and broadcast externally. The CLI never touches keys.
  • execute-* — signs and broadcasts end-to-end via OWS. Use when the caller has run create-wallet (or has any OWS keystore in ~/.ows/wallets/) and wants the CLI to finish the job. Returns confirmed transaction hashes.

Read the full file on GitHub · 157 lines

Files

What ships with it

3 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. 11d ago First seen · 157 lines · 192 tokens per session scan A 127b12d64a78

Subscribe to this mod's changes

robotmoney-cli is a skill published in the GitHub repository robotmoney/robotmoney-skills-v0 (2 stars, last pushed 2mo ago), licensed MIT. It adds 192 tokens to every session and 2,688 once invoked, about $0.0010 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 2026-08-31.