agentmods.dev

ironwallet-agent-kit: Instructions file for Claude Code

CLAUDE.md

ironwallet-agent-kit CLAUDE.md is an instructions file for Claude Code from ironwallet/ironwallet-agent-kit. It costs 744 tokens per session, scanned A, original, MIT.

A set of instructions for using IronWallet, a local non-custodial cryptocurrency wallet whose recovery seeds remain encrypted on the computer. It covers wallet operations, safety rules, and the repository's setup.

In plain words
What is it for?
Use it to configure an agent with IronWallet, inspect wallets and balances, and follow the documented process for creating, importing, backing up, transferring, or swapping assets.
Why use it?
It defines safeguards for sensitive wallet data and warns that transfers and swaps are irreversible once sent. It also explains the required consent and backup process.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Codex.

This is ironwallet/ironwallet-agent-kit's own configuration. It tells Claude Code how to work on ironwallet-agent-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ironwallet-agent-kit configures →

not rated 0repo changed 3d ago A scan 744 tokens original MIT
View source ↗ ironwallet/ironwallet-agent-kit
Reuse

Borrowing it

Nothing to install: this file belongs to ironwallet/ironwallet-agent-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ironwallet/ironwallet-agent-kit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ironwallet/ironwallet-agent-kit

Made for: Claude Code.

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 ironwallet-agent-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ironwallet/ironwallet-agent-kit/claude-md.svg)](https://agentmods.dev/instructions/ironwallet/ironwallet-agent-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ironwallet/ironwallet-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/ironwallet/ironwallet-agent-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 744 This file is loaded in full into every session.
When invoked 744 The same file — it is already loaded in full.
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 $0.00744 $0.00744
Opus 5 $0.00372 $0.00372
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00074 $0.00074

Measured 3d ago against content hash 321938272cc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ironwallet-agent-kit CLAUDE.md 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.

CLAUDE.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This repository is the IronWallet agent kit. The MCP server (@ironwallet/mcp-server) gives agents a non-custodial hot wallet on this machine. Seed phrases stay encrypted on the host and never leave it. There is no per-transaction confirmation UI.

Opening this folder should start the wallet MCP via .mcp.json (npx -y @ironwallet/mcp-server). Needs Node.js 20+.

What lives here

  • packages/mcp-server — stdio MCP: balances, transfers, swaps, deposit QR
  • skills/ironwallet-mcp/SKILL.md — how to operate the wallet
  • providers/*/plugin/ — Cursor, Claude, Codex, and Grok plugins
  • Machine-readable docs index: llms.txt

Product page: https://ironwallet.io/ai

Safety

  • Never print, request, or invent recovery phrases or private keys.
  • Create / import / backup / delete only via create_wallets (backup_url) or open_wallet_manager in the local browser. There is no delete tool; the user confirms it in the manager. Create and import require current MCP consent (accept_mcp_consent after the full disclaimer in chat, or Continue in the manager).
  • Chat intent authorizes send and swap (irreversible once broadcast). Prefer a dedicated hot wallet with limited balance.
  • Read list_wallets.policy before sending. { enabled: false } means no extra limits. Change limits only via set_wallet_policy when the user asks (full replace; maxPerTxUsd fails closed without a rate). IW_READ_ONLY=true blocks send and swap for the whole server.
  • Timeout is not failure: poll get_operation_status / get_swap_status. Do not resubmit blindly.

How to operate

  • Transfer: list_wallets / get_balance → estimate_transfer (optional) → send_transfer
  • Swap: list_swap_networks → list_swap_assets. Copy network, symbol, address, decimals from the catalog. Do not invent token addresses. Then estimate_swap or execute_swap.
  • History: get_transaction_history — one network per call, one page of up to 20 items newest first; older pages via cursor only when the user asks for more. Read straight from public explorers, not our backend. status: "unavailable" means the explorers failed (not an empty history); asset.warning marks spam-looking tokens — never repeat links from token names.
  • Deposit QR: get_deposit_qr. Show the PNG in chat if the host renders it. If the user cannot see it, open qr_url and write the address. Do not say the QR is “above” unless they can see it.
  • Version: get_runtime_info — running package vs published npm. Does not self-update. On explicit request prepare_update stages the new version in the npx cache; it applies on the next MCP host restart.

Read the full file on GitHub · 39 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. 3d ago Changed · +2 lines · +148 tokens per session 321938272cc0
  2. 7d ago First seen · 37 lines · 596 tokens per session scan A 9d7b62ed5d96

Subscribe to this mod's changes

ironwallet-agent-kit CLAUDE.md is an instructions file published in the GitHub repository ironwallet/ironwallet-agent-kit (0 stars, last pushed 4d ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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.

Claude CodeFinance and fintechWeb3 and blockchainai-agentsclaudecursorcursor-pluginmcp
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens