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.
npx skills add openfort-xyz/agent-skills --skill backend-walletgit clone --depth 1 https://github.com/openfort-xyz/agent-skillsWrote 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.
[](https://agentmods.dev/skills/openfort-xyz/agent-skills/backend-wallet)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
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.
- 11d ago First seen · 884 lines · 190 tokens per session scan A 3389582c581a
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.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…