web3agent CLAUDE.md

A project instruction file for a Web3 MCP proxy server, which gives coding agents access to blockchain tools through one interface. It records commands, coding rules, architecture, and tool schemas.

In plain words
What is it for?
Use it when changing the server, running checks, following its two-layer design, or working with blockchain tool integrations.
Why use it?
It gives contributors a shared reference for how to build, test, format, and operate the project correctly.

Instructions file

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.

agentmods
npx agentmods add instructions/apegurus/web3agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/Apegurus/web3agent
Per session 1,977 This file is loaded in full into every session.
When invoked 1,977 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01977 $0.01977
Opus 5 $0.00988 $0.00988
Sonnet 5 $0.00395 $0.00395
Haiku 4.5 $0.00198 $0.00198

Measured 2d ago against content hash d987dae4306f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web3agent 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 2d 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — web3agent

Web3 MCP proxy server that gives AI agents (Claude Code, Cursor, Windsurf, OpenCode) blockchain capabilities through a single install.

Quick Commands

pnpm run lint          # Biome check
pnpm run lint:fix      # Biome auto-fix
pnpm run typecheck     # tsc --noEmit
pnpm run build         # tsup (ESM + DTS)
pnpm test              # vitest run (580+ tests)
pnpm test -- --run tests/path/file.test.ts  # single test file

All four must pass before committing: pnpm run lint && pnpm run typecheck && pnpm run build && pnpm test

Key Conventions

  • ESM only — all imports use .js extension (import { foo } from "./bar.js")
  • stdout is reserved for MCP protocol messages. All logging goes to process.stderr.write() with module prefix: [module-name] message. Never console.log.
  • Type safetycatch (e: unknown) always. No @ts-ignore or @ts-expect-error. as any only with biome-ignore explaining the SDK constraint.
  • Import style — prefer import type { Foo } for type-only imports. Group: Node builtins, external packages, internal modules.

Two-Layer Architecture

This package serves two audiences and every feature must work for both:

  1. MCP tool layer (src/tools/) — AI agents (Claude Code, Cursor, etc.) discover and call tools via the MCP protocol. Tools are registered in src/tools/<group>/index.ts.
  2. Programmatic SDK layer (src/api/, src/index.ts) — downstream projects (e.g. Orbzy) import { ... } from "web3agent" and call functions directly. SDK functions invoke tools via getRuntime() + invokeAndRequireData(runtime, toolName, params) from src/api/shared.ts.

SDK entry points by domain:

Domain File Pattern Example
Swaps & bridge src/api/swaps.ts Runtime → tool invocation getSwapQuote(), executeSameChainSwap()
Intents (external signing) src/api/intents.ts Wraps operations.ts prepareSwapIntent(), prepareOrderIntent()
Orders src/api/orders.ts Runtime → tool invocation listOrders(), placeOrder(), cancelOrder()
Operations (staged) src/api/operations.ts Multi-integration dispatch prepareOperation(), resumeOperation()
Chains src/api/chains.ts Direct + runtime getChain(), listSupportedChains()
Tokens src/api/tokens.ts Direct resolveToken(), listChainTokens()
Simulation src/api/simulation.ts Direct simulateTransaction()
Explorer src/api/explorer.ts Runtime → tool invocation getAddressInfo(), getTransactionHistory()

Read the full file on GitHub · 110 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. 2d ago First seen · 110 lines · 1,977 tokens per session scan A d987dae4306f

Subscribe to this mod's changes

web3agent CLAUDE.md is an instructions file published in the GitHub repository Apegurus/web3agent (1 stars, last pushed 6d ago), licensed MIT. It adds 1,977 tokens to every session, about $0.0099 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.