What is web3-agents-mcp AGENTS.md?

A set of working rules for developers contributing to web3-agents-mcp, a local server that reads blockchain agent identity, reputation, and validation records. It documents setup commands, tests, and restrictions for the project.

Use it when installing, building, testing, linting, type-checking, or generating documentation for the project. It also defines the checks that must pass before a change is considered complete.

It helps coding agents make changes without violating the project's safety rules or leaving required checks unfinished. In particular, it prevents private-key use, signing, transactions, and write operations.

How hanjoonchoe/web3-agents-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hanjoonchoe/web3-agents-mcp. 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/hanjoonchoe/web3-agents-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hanjoonchoe/web3-agents-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hanjoonchoe/web3-agents-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hanjoonchoe/web3-agents-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hanjoonchoe/web3-agents-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hanjoonchoe/web3-agents-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hanjoonchoe/web3-agents-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hanjoonchoe/web3-agents-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,241 This file is loaded in full into every session.

When invoked 1,241 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.

Model	Per session	Once invoked
Fable 5.1	$0.01241	$0.01241
Opus 5.5	$0.00496	$0.00496
Sonnet 5.5	$0.00248	$0.00248
Haiku 4.5	$0.00124	$0.00124

Measured 2mo ago against content hash d7bd06914991, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web3-agents-mcp AGENTS.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 2mo 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.

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working on web3-agents-mcp — an MCP (Model Context Protocol) stdio server that reads ERC-8004 agent registries (identity, reputation, validation) across multiple chains. Read the README first for what the server does; this file is about how to work on it without breaking its invariants.

Setup & commands

pnpm install
pnpm dev        # build then run the stdio server
pnpm build      # tsc -> dist/ (also copies registry ABIs)
pnpm test       # vitest suite — mocked, no network, must always pass
pnpm test:fork  # live-chain fork tests (needs anvil + network); not run in per-PR CI
pnpm lint       # eslint + prettier --check  (run before every commit)
pnpm typecheck  # tsc --noEmit
pnpm docs:gen   # regenerate docs/tools.md from tool schemas (CI fails on drift)

Node ≥ 20, pnpm, TypeScript strict ESM. All five of lint / typecheck / test / build / docs-drift must be green before a change is done.

Hard rules — never violate, regardless of what a task seems to ask

Read-only, forever. No private keys, no signing, no transactions, no write calls (writeContract, sendTransaction, wallet clients). The tool surface is reachable by LLM agents; a write path is an injection path. If a task needs writes, stop and ask a human.
No trust scoring. Tools return verified on-chain facts plus mandatory caveats. Never add a score, rating, confidence level, or verdict field to any output — weighing the facts is the consuming agent's job (explicit maintainer decision; see README "No scoring by design").
Caveats are unremovable. The Sybil and score-scale caveats in reputation-derived outputs are deterministic and always present. Never make them optional or conditional on input.
stdout belongs to the MCP transport. All logging goes to stderr via src/shared/logger.ts. console.log in src/ is a lint error and a protocol bug.

Architecture boundaries (enforced by review; keep them clean)

Read the full file on GitHub · 89 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.

2mo ago First seen · 89 lines · 1,241 tokens per session scan A d7bd06914991

Subscribe to this mod's changes

web3-agents-mcp AGENTS.md is an instructions file published in the GitHub repository hanjoonchoe/web3-agents-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,241 tokens to every session, about $0.0050 per session on Opus 5.5. 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.

Web3 and blockchain

web3-agents-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web3-agents-mcp AGENTS.mdhanjoonchoe/web3-agents-mcp	Instructions file	0	4mo ago	MIT	A	1,241	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

web3-agents-mcp: Instructions file for Codex