gno AGENTS.md

A project instruction file that tells a coding agent how to work in a Bun-based JavaScript and TypeScript project. It covers preferred commands, Bun’s built-in APIs, testing, and model-name freshness.

In plain words
What is it for?
Running scripts, installing packages, building files, loading environment settings, serving HTTP, testing, and tracking work with the project’s Flow-Next commands.
Why use it?
It keeps the agent aligned with the project’s chosen tools and avoids outdated model suggestions or unnecessary Node.js alternatives.

Instructions file for CodexOpenCode

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/gmickel/gno/agents-md
Clone the repo
git clone --depth 1 https://github.com/gmickel/gno

Made for: Codex, OpenCode.

Per session 7,530 This file is loaded in full into every session.
When invoked 7,530 The same file — it is already loaded in full.
Security scan A 2 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 $0.07530 $0.07530
Opus 5 $0.03765 $0.03765
Sonnet 5 $0.01506 $0.01506
Haiku 4.5 $0.00753 $0.00753

Measured 3d ago against content hash d71c6b033a2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gno AGENTS.md scanned grade A with 2 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Verify with `curl -fsSI https://gno.sh`, `ssh [email protected] "systemctl is-active gno-sh"`, and confirm remote `git rev-parse --short HEAD` matches `origin/main`.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| Shell commands | `Bun.$\`cmd\`` | execa, child_process |
AGENTS.md · 648 lines

How it starts

The opening of the file, as written. The whole thing — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KNOWLEDGE CUTOFF WARNING

DO NOT suggest outdated models due to knowledge cutoff. Current models (2026):

  • OpenAI: gpt-5.5
  • Anthropic: claude-opus-4.5, claude-sonnet-4.5, claude-haiku-4.5

When in doubt about model names, ASK the user rather than defaulting to outdated versions.


Note: This project uses Flow-Next for issue tracking. Use .flow/bin/flowctl commands instead of markdown TODOs.

Default to using Bun instead of Node.js.

  • Use bun <file> instead of node <file> or ts-node <file>
  • Use bun test instead of jest or vitest
  • Use bun build <file.html|file.ts|file.css> instead of webpack or esbuild
  • Use bun install instead of npm install or yarn install or pnpm install
  • Use bun run <script> instead of npm run <script> or yarn run <script> or pnpm run <script>
  • Bun automatically loads .env, so don't use dotenv.

APIs - BUN FIRST!

CRITICAL: Always prefer Bun native APIs over Node.js equivalents. Search for Bun alternatives before using node:* imports.

Must Use Bun

Task Use This NOT This
HTTP server Bun.serve() express, fastify, koa
SQLite bun:sqlite better-sqlite3, sqlite3
Redis Bun.redis ioredis, redis
Postgres Bun.sql pg, postgres.js
WebSockets WebSocket (built-in) ws
File read/write Bun.file(), Bun.write() node:fs readFile/writeFile
File existence Bun.file(path).exists() node:fs stat/access
Shell commands Bun.$\cmd`` execa, child_process
YAML Bun.YAML js-yaml, yaml
Env loading (automatic) dotenv

Read the full file on GitHub · 648 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 First seen · 648 lines · 7,530 tokens per session scan A d71c6b033a2d

Subscribe to this mod's changes

gno AGENTS.md is an instructions file published in the GitHub repository gmickel/gno (109 stars, last pushed 3d ago), licensed MIT. It adds 7,530 tokens to every session, about $0.0377 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.