What is artbot AGENTS.md?

A project guide for ArtBot, a Discord bot that answers art-token queries, reports OpenSea activity, announces mints and runs scheduled trivia. It gives coding agents and maintainers the project’s commands, production settings and architecture.

Use it when changing, testing, generating code for or deploying ArtBot. It also helps agents understand how the long-running Node process and its external services fit together.

It keeps agents and maintainers aligned with the repository’s actual behavior and deployment setup. It also records the correct Node, Yarn and code-generation workflow.

artbot AGENTS.md — Instructions file by ArtBlocks

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/artblocks/artbot/agents-md

Clone the repo

git clone --depth 1 https://github.com/ArtBlocks/artbot

Made for: Codex, OpenCode.

Per session 2,561 This file is loaded in full into every session.

When invoked 2,561 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.

Model	Per session	Once invoked
Fable 5	$0.02561	$0.02561
Opus 5	$0.01281	$0.01281
Sonnet 5	$0.00512	$0.00512
Haiku 4.5	$0.00256	$0.00256

Measured 2d ago against content hash e5b0c35978dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

artbot 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 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.

AGENTS.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ArtBot — Agent & Maintainer Guide

Canonical context for AI agents (Cursor, Claude Code, etc.) and human maintainers. Prefer this file over the README when they disagree; keep both in sync when you change behavior.

What this is

ArtBot is the Art Blocks Discord bot: project/token queries (#42 fidenza), OpenSea sales/listings feeds, mint announcements (Hasura webhook), optional Twitter sale posts, and scheduled trivia.

It is a single long-running Node process (Express HTTP + Discord.js + OpenSea stream). Hosted on Render.com (see comment in src/index.ts). There is no Dockerfile in-repo; deploy is yarn start with env vars set in the host.

Quick commands

corepack enable          # Yarn 4 via packageManager field
yarn install             # also runs postinstall → yarn codegen
yarn start               # ts-node src/index.ts
yarn codegen             # regenerate generated/graphql.ts from Hasura schema
yarn lint
yarn format
yarn lint-and-format

Node: 20.x (see .node-version, engines)
Package manager: Yarn 4.3.1 (nodeLinker: node-modules) — do not switch to npm for day-to-day work
generated/ is gitignored — a fresh clone must yarn install or yarn codegen before TypeScript works
Pre-commit (husky): yarn codegen && yarn lint-and-format
Tests: yarn test exists but there are no test files; CI does not run Jest
CI (.github/workflows/build-check.yml): install → codegen → timeout 1m yarn start with PRODUCTION_MODE=false (exit 124 = success)

Two production flags (critical)

These are independent. Mis-setting them is the most common ops footgun.

Env var	Controls	Prod value	Local Discord testing
`ARTBOT_IS_PROD`	Which JSON configs load (`channels.json` / `projectBots.json` vs `*_dev.json`)	`true`	`false` (a-t test server channels)
`PRODUCTION_MODE`	Discord login, then OpenSea event handling / REST poll bot	`true`	`true` if you want live Discord/OpenSea; CI uses `false`

Read the full file on GitHub · 168 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.

2d ago First seen · 168 lines · 2,561 tokens per session scan A e5b0c35978dc

Subscribe to this mod's changes

artbot AGENTS.md is an instructions file published in the GitHub repository ArtBlocks/artbot (44 stars, last pushed 6d ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0128 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 2026-08-30.

Planning Testing bot discord discord-bot

artbot AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ArtBot — Agent & Maintainer Guide

What this is

Quick commands

Two production flags (critical)

What this file has done since we first saw it

Other instructions, from other repositories

WhatsAppToDiscord AGENTS.md

DiscordMCP CLAUDE.md

discord-mcp AGENTS.md

discord-mcp CLAUDE.md

gemini-discord AGENTS.md

discoclaw CLAUDE.md