starknet-anonymous-wallet

starknet-anonymous-wallet is a skill for Claude Code, Codex from keep-starknet-strange/starknet-agentic. It costs 32 tokens per session (1,690 once invoked), scanned A, original, MIT.

A guide for creating and using privacy-focused Starknet wallets through Typhoon, then reading from or sending transactions to Starknet smart contracts.

In plain words
What is it for?
Use it to create or load a Typhoon account, inspect contract interfaces, simulate transactions, check token allowances, or call contracts.
Why use it?
It provides a wallet workflow for agents that need to interact with Starknet while keeping the wallet context anonymous.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present.

Part of the starknet-agentic-skills plugin — 19 skills, 2 commands, 1 plugin shipped together

Good fit Use it to create or load a Typhoon account, inspect contract interfaces, simulate transactions, check token allowances, or call contracts.

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

Made for: Claude Code, Codex.

Or install starknet-agentic-skills, the plugin that ships this one along with the rest of its 19 skills, 2 commands, 1 plugin.

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 starknet-anonymous-wallet

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/keep-starknet-strange/starknet-agentic/starknet-anonymous-wallet"><img src="https://agentmods.dev/badge/skills/keep-starknet-strange/starknet-agentic/starknet-anonymous-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,690 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. Third-party audits
  • 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 $0.00032 $0.01690
Opus 5 $0.00016 $0.00845
Sonnet 5 $0.00006 $0.00338
Haiku 4.5 $0.00003 $0.00169

Measured 11d ago against content hash 00c90b5c56af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

starknet-anonymous-wallet 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.

The scan reads SKILL.md. This mod also ships 14 executable files (scripts/_keys.js, scripts/_rpc.js, scripts/_tokens.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/starknet-anonymous-wallet/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

typhoon-starknet-account

This skill provides agent-facing scripts for:

  • Creating/loading a Starknet account (Typhoon flow)
  • Discovering ABI / functions
  • Reading & writing to contracts
  • Preflight (simulate + fee estimate)
  • Allowance checks with human amounts

When to Use

  • Creating or operating privacy-focused Starknet accounts through the Typhoon flow.
  • Running agent-side contract reads, writes, preflight simulation, or allowance checks from an anonymous wallet context.

When NOT to Use

  • Standard non-private wallet management, DeFi routing, or payment-link flows.
  • Cairo contract authoring, deployment operations, or security audits.

Quick Start

  • Deep dives: references/ (ABI discovery, Typhoon account flow, preflight/fee simulation notes)
  • Adjacent modules: skills catalog
  • Account flow examples: scripts/create-account.js, scripts/parse-smart.js, scripts/resolve-smart.js
  • Read/write examples: scripts/read-smart.js, scripts/invoke-contract.js, scripts/avnu-swap.js
  • Allowance checks example: scripts/read-smart.js (call ERC20 allowance(owner, spender))

Prerequisites

npm install starknet@^8.9.1 typhoon-sdk@^1.1.13 @andersmyrmel/vard@^1.2.0 @avnu/avnu-sdk compromise@^14.14.5 ws@^8.19.0

RPC setup (required for onchain reads/writes)

These scripts talk to Starknet via JSON-RPC. Configure one of:

  • Set STARKNET_RPC_URL in your environment (recommended), OR
  • Pass rpcUrl in the JSON input for scripts that support it.

If neither is provided, scripts fall back to the public Lava mainnet RPC:

  • https://rpc.starknet.lava.build:443

Starknet.js v8.9.1 quick patterns

import { RpcProvider, Account, Contract } from 'starknet';

const provider = new RpcProvider({
  nodeUrl: process.env.STARKNET_RPC_URL || 'https://rpc.starknet.lava.build:443'
});

// signer can be a private key string or Starknet Signer instance
const account = new Account({
  provider,
  address: process.env.ACCOUNT_ADDRESS,
  signer: process.env.PRIVATE_KEY
});

const contract = new Contract({
  abi,
  address: contractAddress,
  providerOrAccount: account
});

// read
const balance = await contract.call('balance_of', [account.address]);

// write (sign -> send -> wait)
const tx = await contract.invoke('transfer', [to, amount], { waitForTransaction: false });
const receipt = await provider.waitForTransaction(tx.transaction_hash);

Read the full file on GitHub · 230 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 · 230 lines · 32 tokens per session scan A 00c90b5c56af

Subscribe to this mod's changes

starknet-anonymous-wallet is a skill published in the GitHub repository keep-starknet-strange/starknet-agentic (80 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 1,690 once invoked, about $0.0002 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 2026-08-30.