expo-mobile-template AGENTS.md

expo-mobile-template AGENTS.md is an instructions file for Codex, OpenCode from kitariel/expo-mobile-template. It costs 4,004 tokens per session, scanned A, original, MIT.

A repository instruction file tells AI coding tools how to work in an Expo mobile app project. Expo is a tool for building React Native apps, which run on phones from shared JavaScript code.

In plain words
What is it for?
For directing assistants to read the current handoff document, follow project conventions, and update the handoff as work progresses.
Why use it?
It gives different coding assistants the same starting information and preserves unfinished work between sessions.

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/kitariel/expo-mobile-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/kitariel/expo-mobile-template

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.

agentmods badge for expo-mobile-template AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kitariel/expo-mobile-template/agents-md.svg)](https://agentmods.dev/instructions/kitariel/expo-mobile-template/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kitariel/expo-mobile-template/agents-md"><img src="https://agentmods.dev/badge/instructions/kitariel/expo-mobile-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,004 This file is loaded in full into every session.
When invoked 4,004 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 5.1 $0.04004 $0.04004
Opus 5 $0.02002 $0.02002
Sonnet 5 $0.00801 $0.00801
Haiku 4.5 $0.00400 $0.00400

Measured 5d ago against content hash f048e5c24593, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

expo-mobile-template 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 5d 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 · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Source of truth for every AI coding tool used in this repo — Claude Code, Codex, Cursor, Copilot, Gemini, Windsurf, or anything else. Other tools' config files are pointers to this one. Edit this file; never fork its content into a tool-specific file.


0. Start here, every session

Read docs/HANDOFF.md before your first edit. It is one file describing where the project stands right now — including work left half-finished by whichever tool ran last.

This repo is expected to be worked on by different assistants at different times: Claude Code until its usage runs out, then Codex, then Cursor, then back again. HANDOFF.md is the baton they pass. It only works if everyone honours both halves of the contract:

Before your first edit Read docs/HANDOFF.md. If its Next step is populated and the user hasn't asked for something else, that is your task.
At every checkpoint Update it. Not at the end — at checkpoints. Usage limits and crashes do not give notice, and a session that dies mid-task leaves nothing behind but this file.

Full rules: .agents/handoff.md.


1. What this repo is

An Expo (React Native) mobile template designed to be cloned and driven by an AI agent. Someone clones it, tells their assistant "give me a dark theme with rounded cards", and the assistant has enough written context here to do it without guessing.

Expo SDK 57
React Native 0.86.2
React 19.2.3 (React Compiler enabled)
Router expo-router v57, file-based, typed routes
Language TypeScript 6, strict: true
Package manager npm (not pnpm — Expo native module resolution)

Phase status

Phase Scope State
0 Expo scaffold, agent layer, docs ✅ done
1 Design system — navigation, headers, auth, cards, drawers, buttons, forms, collections, charts, calendars, icons, tokens ✅ done
2a Named theme presets ✅ done
2b UX/UI review agents ⏳ not started — do not start without the maintainer's signal

Read the full file on GitHub · 288 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. 5d ago First seen · 288 lines · 4,004 tokens per session scan A f048e5c24593

Subscribe to this mod's changes

expo-mobile-template AGENTS.md is an instructions file published in the GitHub repository kitariel/expo-mobile-template (6 stars, last pushed 13d ago), licensed MIT. It adds 4,004 tokens to every session, about $0.0200 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 2026-08-31.