agentic-wallet

agentic-wallet is a skill for Claude Code from coinbase/agentic-wallet-skills. It costs 139 tokens per session (1,089 once invoked), scanned A, original, MIT.

A command-line tool for operating a cryptocurrency wallet. It supports signing in, viewing balances, sending and trading tokens, adding funds, and using x402, a system for paying for online services with cryptocurrency.

In plain words
What is it for?
Use it to authenticate a wallet, check USDC, ETH, POL, or SOL balances, transfer or trade tokens, fund the wallet, and discover or pay for x402 services and APIs.
Why use it?
It puts common wallet and paid-service actions into commands instead of requiring separate websites or manual blockchain steps.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

not rated 126repo 1mo ago A scan Socket: warnSnyk: failSkillSpector: pass 139 tokens original MIT

Good fit Use it to authenticate a wallet, check USDC, ETH, POL, or SOL balances, transfer or trade tokens, fund the wallet, and discover or pay for x402 services and APIs.

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

Made for: Claude Code.

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 agentic-wallet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/coinbase/agentic-wallet-skills/agentic-wallet"><img src="https://agentmods.dev/badge/skills/coinbase/agentic-wallet-skills/agentic-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,089 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. Third-party audits
  • Socket warn 5 Aug 2026
  • Snyk fail 5 Aug 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00139 $0.01089
Opus 5 $0.00069 $0.00544
Sonnet 5 $0.00028 $0.00218
Haiku 4.5 $0.00014 $0.00109

Measured 10d ago against content hash 063480c1e450, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentic-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 10d 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.

allowed-tools: ["Bash(npx [email protected] *)", "Bash(npm *)", "Bash(node *)", "Bash(curl *)", "Bash(mkdir *)"]
skills/agentic-wallet/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Wallet

Operate a crypto wallet through the awal CLI. This skill is a router: read the relevant reference file in references/ for the task at hand.

Preflight: Confirm wallet state

Before any wallet operation that requires authentication (everything except x402 search/details), check status:

npx [email protected] status

If the wallet is not authenticated, read references/auth.md and complete sign-in first.

Routing

Pick the reference that matches the task and Read it before acting:

Task Reference
Sign in, log in, connect wallet, OTP verification, "not signed in" errors references/auth.md
Check balances, "how much USDC/ETH/POL/SOL do I have", balance per chain, JSON balance output references/balance.md
Send USDC / ETH / POL / SOL to an address or ENS name (Base, Polygon, Solana) references/send-usdc.md
Swap / trade / convert tokens on Base or Polygon references/trade.md
Add funds, top up, onramp, buy USDC references/fund.md
Find / browse / search paid services on the x402 bazaar references/x402-search.md
Call a paid x402 API endpoint with automatic USDC payment references/x402-pay.md
Build or deploy a paid API server that other agents can pay to use references/x402-monetize.md
Query onchain data on Base (events, transactions, blocks) via the CDP SQL API references/query-onchain.md

If no clear match and the user wants an external capability, search the x402 bazaar (references/x402-search.md) — a paid service may exist.

Shared rules

  • Input validation: every reference lists the regexes / allowlists that user-provided values must match before being placed in a shell command. Validate strictly; reject inputs containing spaces, semicolons, pipes, backticks, or other shell metacharacters. Do not pass unvalidated user input into commands.
  • Single-quote $ amounts: any amount written as '$1.00' must be single-quoted to prevent bash variable expansion.
  • JSON output: every awal command supports --json for machine-readable output.
  • Auth errors mean re-auth: if any command fails with "Not authenticated" or similar, read references/auth.md and run the sign-in flow.
  • Insufficient balance: read references/fund.md to top up.

Read the full file on GitHub · 66 lines

Files

What ships with it

9 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. 10d ago First seen · 66 lines · 139 tokens per session scan A 063480c1e450

Subscribe to this mod's changes

agentic-wallet is a skill published in the GitHub repository coinbase/agentic-wallet-skills (126 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 1,089 once invoked, about $0.0007 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 2026-08-30.