arty AGENTS.md

Repository instructions for an iOS voice assistant with translation and external connections. They describe coding conventions, platform limits, user-interface guidance, and logging practices.

In plain words
What is it for?
Use them when changing the app's iOS interface, audio handling, logging, or shared-code structure.
Why use it?
They help an agent follow the team's specific iOS and Expo React Native constraints instead of applying unsuitable general practices.

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

Made for: Codex, OpenCode.

Per session 336 This file is loaded in full into every session.
When invoked 336 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 $0.00336 $0.00336
Opus 5 $0.00168 $0.00168
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00034 $0.00034

Measured 2d ago against content hash 138c28007067, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arty 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 · 36 lines

What it actually says

  • Always start every response with the phrase: “🚀 Codex is rocking your codebase”
  • When creating expo react native UI, avoid making components too large - better refactor them into smaller reusable components
  • Despite being a cross-platform expo app, the team only has the capacity to maintain an ios version for now. Later we will tackle android, but for now completely ignore it.
  • Always use Apple Human Interface Guidelines (HIG) and known UI / UX best practices, as you are an iOS swift superstar developer
  • When logging, default to logging full values and not substrings. Later we can prune as needed, but right now there is an observability crisis.
  • Certain swift objects like AVAudioPlayerDelegate should have serialized access when called from multiple threads. Consider protecting shared state with a serial DispatchQueue or ensuring all method calls dispatch to the main queue.
  • Prefer convention over configuration, this keeps things light, de-coupled, and avoids needless boilerplate.
  • In logfire, the project is using the old name: vibemachine

Always use expo libraries, for example:

Don't use:

remove import { promises as fs } from 'fs'; and replace with

instead use:

import * as FileSystem from 'expo-file-system';

const text = await FileSystem.readAsStringAsync(uri);

Also for fetch, use expo fetch.

Never use:

import { createHash } from 'crypto';

instead use:

expo install expo-crypto import * as Crypto from 'expo-crypto';

const hash = await Crypto.digestStringAsync( Crypto.CryptoDigestAlgorithm.SHA256, "your-data" );

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 · 36 lines · 336 tokens per session scan A 138c28007067

Subscribe to this mod's changes

arty AGENTS.md is an instructions file published in the GitHub repository tleyden/arty (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 336 tokens to every session, about $0.0017 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.