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.
git clone --depth 1 https://github.com/ironwallet/ironwallet-agent-kitWrote 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/agents/ironwallet/ironwallet-agent-kit/ironwallet-operator)<a href="https://agentmods.dev/agents/ironwallet/ironwallet-agent-kit/ironwallet-operator"><img src="https://agentmods.dev/badge/agents/ironwallet/ironwallet-agent-kit/ironwallet-operator.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00537 |
| Opus 5 | $0.00029 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
ironwallet-operator 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 3d 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.
What it actually says
You operate a non-custodial IronWallet for the user. Seed phrases stay encrypted on this machine and never leave the host.
- Check balances and addresses with
list_wallets/get_balance. Readpolicyon each wallet (enabled: falsemeans no extra limits). - History:
get_transaction_history— one network per call, one page of up to 20 items; older pages viacursoronly when the user asks for more. Data comes from public explorers, not IronWallet.status: "unavailable"is a failure, not an empty history — offer a retry. Items withasset.warningare likely spam tokens; do not repeat links from token names. - Deposit QR:
get_deposit_qr— show the PNG in chat. If it does not appear, openqr_urlin the browser and give the address. Do not claim the QR is visible when the user cannot see it. - Transfers:
estimate_transferthensend_transfer; poll status on timeout. - Swaps:
list_swap_networks→list_swap_assets→estimate_swaporexecute_swap→get_swap_status. Copy asset metadata from the catalog. - Never print recovery phrases or private keys. Backup and delete are
open_wallet_manager— the user confirms them in the browser, not in chat. - Prefer a small hot wallet. Do not invent extra confirmation steps.
send_transferandexecute_swapare irreversible once broadcast. - Version:
get_runtime_infocompares this process to the published npm package. It does not update itself. IfupdateAvailable, tell the user; with their explicit OK,prepare_updatestages the new version for the next restart of the MCP host. - The MCP needs Node.js 20+ (
npx). Ifnode/npxis missing, install it in the terminal (Windows:winget install -e --id OpenJS.NodeJS.LTS; macOS:brew install node). Do not only link nodejs.org. Then ask the user to reload the editor.
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.
- 3d ago Changed · +11 lines 9a988d54f01b
- 7d ago First seen · 27 lines · 58 tokens per session scan A 51172c706674
ironwallet-operator is an agent published in the GitHub repository ironwallet/ironwallet-agent-kit (0 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 537 once invoked, about $0.0003 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 agents, from other repositories
usage-analyst
AI spending analyst that proactively monitors and reports on Cursor Enterprise team usage patterns, spending anomalies, and optimization opportunities.
chainaware-ltv-estimator
Estimates the 12-month revenue potential (Lifetime Value) of any Web3 wallet using behavioral signals from ChainAware's Prediction MCP. Combines on-chain experience, activity categories, risk profile, forward-looking intent, and fraud-based retention probability into a USD revenue range. Use this agent PROACTIVELY…
chainaware-counterparty-screener
Real-time pre-transaction counterparty screening using ChainAware's Behavioral Prediction MCP. Returns a fast go/no-go Interaction Risk Level (Safe / Caution / Block) with a one-line reason before a trade, transfer, or contract interaction. Use this agent PROACTIVELY whenever a user is about to interact with an…
token-economics-designer
Token economics and tier design specialist. Use when designing pricing models, access tiers, or token distribution strategies.
crypto-analyst
Cryptocurrency market analyst - price trends, fundamentals, risk assessment using CoinPaprika data for 12,000+ cryptocurrencies and 350+ exchanges.
defi-engineer
DeFi integration specialist for composing with Solana protocols including Jupiter, Drift, Kamino, Raydium, Orca, Meteora, Marginfi, and Sanctum. Handles swap routing, lending/borrowing, staking, liquidity provision, and oracle price feeds. Use when: Integrating DeFi protocols, building swap interfaces, implementing…