What is expo-forge AGENTS.md?

Project instructions for Expo Forge, an Expo SDK 56 application built with React Native and TypeScript that can also run on the web. They cover its libraries, package manager, UI components, testing, and development rules.

Use them when changing screens, navigation, native or web code, UI components, Convex or authentication integrations, tests, or build and formatting scripts.

They prevent changes that conflict with the project’s pinned versions, chosen tools, component system, or required quality checks.

How ajayyAI/expo-forge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ajayyAI/expo-forge. 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/ajayyAI/expo-forge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ajayyAI/expo-forge

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/ajayyai/expo-forge/agents-md/github.svg)](https://agentmods.dev/instructions/ajayyai/expo-forge/agents-md)

Your own site

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

Per session 1,259 This file is loaded in full into every session.

When invoked 1,259 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	$0.01259	$0.01259
Opus 5.5	$0.00504	$0.00504
Sonnet 5.5	$0.00252	$0.00252
Haiku 4.5	$0.00126	$0.00126

Measured 2mo ago against content hash 33cda83ca136, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

expo-forge 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Claude Code, Cursor, Copilot, etc.) working in Expo Forge. Humans: this doubles as a conventions cheat-sheet.

Expo moves fast. Read the exact versioned docs at https://docs.expo.dev/versions/v56.0.0/ before writing native or SDK code — your training data may be stale.

Stack at a glance

Expo SDK 56 · React 19.2 · React Native 0.85 · New Architecture · Expo Router (typed routes) · web export.
Package manager: bun. Never use npm, yarn, pnpm, or npx. Use bun install, bun run <script>, bunx <tool>.
Node 24 LTS (pinned in .nvmrc); >=20.19.4 is the supported floor in package.json engines. Tooling runs on Node; bun is only the package manager.
UI: Uniwind + Tailwind v4 (engine) → HeroUI Native (@/components/ui) → @expo/ui (native primitives). Prefer existing @/components/ui components before reaching for raw RN.
Backend (optional): Convex + Better Auth. Off by default. Keep it cleanly removable.
Lint/format: Biome via Ultracite. Tests: Jest + React Native Testing Library + convex-test.
Lang: TypeScript strict. Imports use the @/* → src/* alias.

Golden rules

bun only. Any npm/yarn/pnpm/npx in a command, script, or doc is wrong.
Keep auth/backend self-contained. Auth code stays under src/features/auth/ and convex/. Route files are thin re-exports. Don't import authClient or api.* outside the auth feature and its existing seams (src/app/_layout.tsx, the AuthGate, src/lib).
Env-gate new integrations. A new third-party service must be a no-op when its env var is unset — the template must stay green on a fresh clone with empty .env. Add the var to env.ts (Zod schema) and document it in .env.example.
No secrets in git. Only .env.example is tracked. Never write real keys into committed files. Server secrets live on the Convex deployment / EAS / CI.
No "AI-slop" comments. Comments explain why, not what. No // import the thing, no narrating the obvious. Match the surrounding code's density and idiom.
No upstream-project names (the templates this derives from) anywhere except CREDITS.md.

Read the full file on GitHub · 75 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 · 75 lines · 1,259 tokens per session scan A 33cda83ca136

Subscribe to this mod's changes

expo-forge AGENTS.md is an instructions file published in the GitHub repository ajayyAI/expo-forge (23 stars, last pushed 5mo ago), licensed MIT. It adds 1,259 tokens to every session, about $0.0050 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.

expo-forge AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
expo-forge AGENTS.mdajayyAI/expo-forge	Instructions file	23	5mo ago	MIT	A	1,259	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

expo-forge: Instructions file for Codex