What is web3gpt AGENTS.md?

Repository instructions for Web3GPT, a Next.js application for chatting with AI agents and developing, deploying, and verifying smart contracts on compatible blockchain test networks.

Working on chat pages and API routes, AI agents, GitHub sign-in, blockchain wallets, Solidity compilation and deployment, saved chats, contract verification, and scheduled jobs.

They identify the project's frameworks, services, authentication, wallet connections, storage, and main user flows so changes can be made in the correct part of the application.

How Markeljan/web3gpt configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Markeljan/web3gpt. 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/Markeljan/web3gpt/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Markeljan/web3gpt

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/markeljan/web3gpt/agents-md/github.svg)](https://agentmods.dev/instructions/markeljan/web3gpt/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/markeljan/web3gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/markeljan/web3gpt/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/markeljan/web3gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/markeljan/web3gpt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,264 This file is loaded in full into every session.

When invoked 2,264 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	$0.02264	$0.02264
Opus 5.5	$0.00906	$0.00906
Sonnet 5.5	$0.00453	$0.00453
Haiku 4.5	$0.00226	$0.00226

Measured 2mo ago against content hash 704fe4e50211, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web3gpt 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Overview

Web3GPT is a single-app Next.js 16 project for AI-assisted smart contract development. The app combines:

App Router pages and API routes
AI SDK chat flows backed by OpenAI models
GitHub authentication via Better Auth
Wallet connectivity through Wagmi and RainbowKit
Contract compilation/deployment helpers built on solc and viem
Persistence in Vercel KV for users, chats, agents, deployments, and verification jobs

Primary product flows:

Chat with built-in or user-created agents
Deploy Solidity contracts to supported EVM testnets
Persist chats for signed-in users and share published chats
Run a Vercel cron to process contract verifications

Stack

Runtime/package manager: Bun (bun.lock is committed)
Framework: Next.js 16 App Router
Language: TypeScript with strict mode
UI: React 19, Tailwind CSS, Radix UI, shadcn/ui-style primitives
AI: Vercel AI SDK (ai, @ai-sdk/react, @ai-sdk/openai)
Auth: better-auth with GitHub provider, stateless (cookie) sessions
Web3: wagmi, viem, @rainbow-me/rainbowkit
Storage/services: @vercel/kv, Vercel Analytics, Pinata
Lint/format: Ultracite/Biome

Common Commands

Install: bun install
Dev server: bun dev
Build: bun run build
Start production server: bun run start
Typecheck: bun run typecheck
Lint: bun run lint
Format: bun run format

Git hooks are managed by lefthook.yml. Pre-commit runs bunx ultracite fix on JS/TS/JSON/CSS files.

Environment

Copy from .env.example. Important groups:

RPC and explorer access: NEXT_PUBLIC_ALCHEMY_API_KEY, NEXT_PUBLIC_TENDERLY_API_KEY, BLOCKSCOUT_API_KEY, ETHERSCAN_API_KEY
Wallet connectivity: NEXT_PUBLIC_WALLETCONNECT_PROJECT_ID
Auth: AUTH_GITHUB_ID, AUTH_GITHUB_SECRET, AUTH_SECRET (Better Auth also accepts BETTER_AUTH_GITHUB_ID, BETTER_AUTH_GITHUB_SECRET, BETTER_AUTH_SECRET)
AI providers: OPENAI_API_KEY, optional XAI_API_KEY, STABILITY_API_KEY
Persistence: KV_REST_API_URL, KV_REST_API_TOKEN, KV_REST_API_READ_ONLY_TOKEN, KV_URL
Deployment/signing: DEPLOYER_PRIVATE_KEY
Cron auth: CRON_SECRET
IPFS uploads: PINATA_JWT and NEXT_PUBLIC_IPFS_GATEWAY (PINATA_API_KEY/PINATA_API_SECRET are legacy and unused by the app)

Read the full file on GitHub · 138 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 · 138 lines · 2,264 tokens per session scan A 704fe4e50211

Subscribe to this mod's changes

web3gpt AGENTS.md is an instructions file published in the GitHub repository Markeljan/web3gpt (118 stars, last pushed 2mo ago), licensed MIT. It adds 2,264 tokens to every session, about $0.0091 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 2026-08-30.

Building agents Web3 and blockchain agents-web3 ai-solidity ai-web3 solidity web3-agents web3-ai

web3gpt AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web3gpt AGENTS.mdMarkeljan/web3gpt	Instructions file	118	2mo ago	MIT	A	2,264	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

web3gpt: Instructions file for Codex