openfort-backend-wallets

openfort-backend-wallets is a skill for Claude Code from openfort-xyz/agent-skills. It costs 190 tokens per session (7,710 once invoked), scanned A, original, MIT.

A server-side Openfort wallet helper for creating and operating developer-controlled wallets on EVM blockchains and Solana. EVM refers to the system used by Ethereum and compatible networks; these wallets can sign messages and transactions without user interaction.

In plain words
What is it for?
Use it for server-controlled wallets, automated transactions, batch minting, payroll, airdrops, AI-agent wallets, private-key operations, message signing, typed-data signing, and EIP-7702 delegation.
Why use it?
It removes the need to build wallet custody and signing flows from scratch for automated backend operations. It also documents the boundary between test wallets and live wallets, which cannot be reused across environments.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the openfort plugin — 4 skills, 2 MCP servers shipped together

Good fit Use it for server-controlled wallets, automated transactions, batch minting, payroll, airdrops, AI-agent wallets, private-key operations, message signing, typed-data signing, and EIP-7702 delegation.

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

Made for: Claude Code.

Or install openfort, the plugin that ships this one along with the rest of its 4 skills, 2 MCP servers.

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 openfort-backend-wallets

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/openfort-xyz/agent-skills/backend-wallet"><img src="https://agentmods.dev/badge/skills/openfort-xyz/agent-skills/backend-wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,710 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 $0.00190 $0.07710
Opus 5 $0.00095 $0.03855
Sonnet 5 $0.00038 $0.01542
Haiku 4.5 $0.00019 $0.00771

Measured 11d ago against content hash 3389582c581a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

openfort-backend-wallets 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.

skills/backend-wallet/SKILL.md · 884 lines

How it starts

The opening of the file, as written. The whole thing — 884 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Openfort Backend Wallets (Developer Custody)

⚠️ Test keys vs. live keys — read before creating any wallet. Openfort runs two fully isolated universes: test mode (sk_test_… / pk_test_…, testnet only) and live mode (sk_live_… / pk_live_…, mainnet, real funds). Objects created in one universe cannot be read, signed with, or recovered from the other.

  • A wallet created with a test (dev) secret key exists only on testnet. It is not usable in production and must never custody or move real funds.
  • To go to production, switch to your live secret key and create fresh wallets — never migrate or reuse test wallets across modes.
  • Secret keys (sk_…) are server-side only. Never commit them or expose them to a client. See https://openfort.io/docs/configuration/api-keys.

Backend wallets are server-controlled EOAs for automated blockchain operations — no user interaction required. Private keys are stored in hardware-backed secure enclaves and never leave the secure environment.

When to use backend wallets (vs embedded wallets):

  • Server-side automation: treasury ops, batch minting, payroll, airdrops
  • AI agent wallets: autonomous trading, payment processing
  • Programmatic signing: no browser or user present
  • Cross-border payments: automated stablecoin disbursement

When to use embedded wallets instead:

  • User-facing wallets where the user controls the key
  • Browser/mobile signing flows with user approval

Setup

npm install @openfort/openfort-node
# EVM peer dependency (required for sendTransaction):
npm install viem
# Solana peer dependencies (required for Solana operations):
npm install @solana/kit @solana-program/system @solana-program/compute-budget @solana-program/token @solana/kora @solana/transaction-confirmation

Environment Variables

OPENFORT_SECRET_KEY=sk_test_...            # Secret API key (required)
OPENFORT_WALLET_SECRET=...              # Base64-encoded EC P-256 private key (required for mutations)
OPENFORT_PUBLISHABLE_KEY=pk_test_...    # Required for Solana operations (Kora gasless)
OPENFORT_BASE_URL=https://api.openfort.io  # Optional, defaults to production

Read the full file on GitHub · 884 lines

Files

What ships with it

5 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 · 884 lines · 190 tokens per session scan A 3389582c581a

Subscribe to this mod's changes

openfort-backend-wallets is a skill published in the GitHub repository openfort-xyz/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 190 tokens to every session and 7,710 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.