aurey-wallet-onboarding

aurey-wallet-onboarding is a skill for Claude Code, Codex from agentic-pantheon/aurey-mcp. It costs 70 tokens per session (2,949 once invoked), scanned C, original, MIT.

An onboarding guide for connecting Aurey Wallet MCP with 1Claw custody through hosts such as Hermes, OpenClaw, or Cursor. It covers setup without handling private keys or other secrets in chat.

In plain words
What is it for?
Use it to install and configure Aurey Wallet MCP, connect 1Claw, and troubleshoot the initial setup.
Why use it?
It helps users connect the wallet safely while keeping sensitive credentials out of the conversation.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to install and configure Aurey Wallet MCP, connect 1Claw, and troubleshoot the initial setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding
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 agentic-pantheon/aurey-mcp --skill aurey-wallet-onboarding
Clone the repo
git clone --depth 1 https://github.com/agentic-pantheon/aurey-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 aurey-wallet-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding/github.svg)](https://agentmods.dev/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding)
Your own site
<a href="https://agentmods.dev/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding"><img src="https://agentmods.dev/badge/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding/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 aurey-wallet-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding"><img src="https://agentmods.dev/badge/skills/agentic-pantheon/aurey-mcp/aurey-wallet-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00070 $0.02949
Opus 5 $0.00035 $0.01474
Sonnet 5 $0.00014 $0.00590
Haiku 4.5 $0.00007 $0.00295

Measured 11d ago against content hash 81a6a7449c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

aurey-wallet-onboarding scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://agentic-pantheon.github.io/aurey-mcp/install.sh | bash

Makes network callslowCapability

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

| [Install site](https://agentic-pantheon.github.io/aurey-mcp/install.html) | curl / PyPI flow (default for users) |
skills/aurey-wallet-onboarding/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aurey Wallet — onboarding (agent skill)

You help the user connect Aurey Wallet MCP with 1Claw Intents custody. You do not handle private keys or API secrets in chat.

Doc Use
Install site curl / PyPI flow (default for users)
llms.txt Machine-oriented install spec
install/hermes.md Hermes + aurey-setup (primary)
docs/1claw-onboarding-guide.md All hosts, manual 1Claw, troubleshooting
ONBOARDING_1CLAW.md One-page reminder

After MCP works, hand off to skills/aurey-wallet/SKILL.md for swaps and sends.


Non-negotiables

  1. Never ask for—or offer to receive—in chat: private keys, mnemonics, 1ck_ (human), ocv_ (agent), Alchemy, LiFi, or Zerion API keys. Do not say “send me the key and I’ll continue”; there is no safe way for the user to give you a secret in chat.
  2. Say it upfront, unprompted. Your first setup message must (a) state that keys must never be pasted in this chat, and (b) give the exact terminal commands to run on the machine where this agent/MCP host is running. Do not wait for the user to ask whether chat is safe. Use the First message template below.
  3. If the user pastes a secret in chat anyway: tell them it may be retained in logs/context, instruct them to rotate it immediately in the issuing dashboard (1Claw / Alchemy / LiFi / Zerion), and continue with the terminal flow using the new key. Never echo the pasted value back.
  4. OK in chat: repo path, vault/agent UUIDs (optional), smoke-test errors (redact secrets), tool JSON from get_agent_wallet_addresses.
  5. Hermes: user runs aurey-setup (or uv run aurey-setup from a dev clone) in a real terminal on the same machine where Hermes runsaurey-setup prompts for keys with masked input there; never pipe chat text into it.
  6. Prefer curl install or pip install 'aurey-wallet-mcp[hermes]'; do not git clone unless the user explicitly wants contributor mode.
  7. Alchemy lives in 1Claw vault api-keys/alchemy (see ~/.aurey/config.toml); not Hermes MCP env.
  8. LiFi API key (optional): stored at api-keys/lifi when set during aurey-setup; lifi_api_secret_path in ~/.aurey/config.toml. Powers LiFi Earn vault discovery (earn_list_vaults, APY/TVL) and higher-rate LiFi quotes; basic swaps may work without it, but Earn (earn.li.fi) requires the key. User gets one via LiFi Earn quickstart (Partner Portal signup → API key). User runs setup in terminal—do not ask for the key in chat.
  9. Zerion API key (optional): stored at api-keys/zerion when set during aurey-setup; zerion_api_secret_path in ~/.aurey/config.toml. Powers Telegram Mini App portfolio charts/balances; skip if the user does not use the Mini App. Get a key at developers.zerion.io—terminal only, not chat.
  10. Never invent 0x — use get_agent_wallet_addresses after MCP is connected.
  11. No tx_execute during onboarding; verification is read-only only.

Read the full file on GitHub · 185 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. 11d ago First seen · 185 lines · 70 tokens per session scan C 81a6a7449c81

Subscribe to this mod's changes

aurey-wallet-onboarding is a skill published in the GitHub repository agentic-pantheon/aurey-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 2,949 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.