agent-wallet

agent-wallet is a skill for Claude Code, Codex from hec-ovi/blockchain-skill. It costs 93 tokens per session (2,223 once invoked), scanned A, a copy of agent-wallet, MIT.

A skill for operating a non-custodial wallet directly on EVM-compatible blockchains and Bitcoin. EVM-compatible networks run Ethereum-style smart contracts.

In plain words
What is it for?
It supports wallet creation and import, balance checks, transfers of native coins and ERC-20 tokens, Bitcoin transfers, swaps, and compiling, deploying, or calling Solidity contracts.
Why use it?
It lets an agent perform wallet and blockchain tasks through a local command-line tool while keeping keys in a local keystore.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It supports wallet creation and import, balance checks, transfers of native coins and ERC-20 tokens, Bitcoin transfers, swaps, and compiling, deploying, or calling Solidity contracts.

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

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 agent-wallet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hec-ovi/blockchain-skill/agent-wallet"><img src="https://agentmods.dev/badge/skills/hec-ovi/blockchain-skill/agent-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,223 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.02223
Opus 5 $0.00046 $0.01111
Sonnet 5 $0.00019 $0.00445
Haiku 4.5 $0.00009 $0.00222

Measured 9d ago against content hash 20e134afdc14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

**Use this CLI only** for wallet/chain ops. Do not quote swaps via random web APIs (0x, Uniswap web, curl to aggregators). `swap-quote` / `swap` on the CLI are the path.
Origin

This is a copy

100% identical to agent-wallet — 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.

plugins/agent-wallet-codex/skills/agent-wallet/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-wallet

Instructions only. Every action is the agent-wallet CLI: one process, JSON envelope {ok, data, error, meta} on stdout, then exit. On ok:false follow error.hint. Keys stay local (keystore v3). No custodial middleman.

Start here

Node >= 22.18. Skill packs ship dist/agent-wallet.mjs (no npm install).

Resolve CLI once (first hit wins; reuse it):

command -v agent-wallet
test -x .noob/skills/agent-wallet/agent-wallet && echo .noob/skills/agent-wallet/agent-wallet
test -f .noob/skills/agent-wallet/dist/agent-wallet.mjs && echo "node .noob/skills/agent-wallet/dist/agent-wallet.mjs"
test -x ./agent-wallet && echo ./agent-wallet

Init once per session:

agent-wallet init

Read data.ready, data.nextActions, data.notes. Do not hand-probe the install.

Passphrase (signing verbs). Do this once, then stop touching it:

  1. If a .env at the project root already has AGENT_WALLET_PASSPHRASE, use it (CLI auto-loads .env). Do not invent another.
  2. Else create .env once with AGENT_WALLET_PASSPHRASE=<random >=8 chars> and AGENT_WALLET_HOME=./.agent-wallet-data (or keep default home). Never print the passphrase in chat.
  3. Run verbs from anywhere in the project: .env is found by walking up, so a scratch subdirectory is fine.
  4. On PASSPHRASE_WRONG: stop. Do not brute-force, dump keystore JSON, or reverse-engineer the bundle.

Fund testnets by receiving from an external wallet or a public testnet drip site. This toolkit does not drip gas.

When to use which

Intent Verb
Session ready? init
New / restore wallet wallet-create / wallet-import
Receive address wallet-addresses
Export key / backup secrets wallet-export (prefer --out)
Balance / fees / tx / UTXOs balance / fees / tx / utxos
Pay someone (native, ERC-20, BTC) send
Same-chain token A → B swap-quote then swap (sell WETH not bare ETH; wrap first if needed)
ETH ↔ WETH wrap / unwrap
Unknown contract contract-learn then call/write
Deploy contract-compile then contract-deploy
Chain meta / RPC alive chain-resolve / chain-check

Read the full file on GitHub · 152 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. 9d ago First seen · 152 lines · 93 tokens per session scan A 20e134afdc14

Subscribe to this mod's changes

agent-wallet is a skill published in the GitHub repository hec-ovi/blockchain-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 2,223 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to agent-wallet, differing in 0 lines, and is treated as a copy.