json-to-compose: Instructions file for Codex

AGENTS.md

json-to-compose AGENTS.md is an instructions file for Codex, OpenCode from jesusdmedinac/json-to-compose. It costs 5,918 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working on json-to-compose, a Kotlin Multiplatform framework that turns JSON data into Jetpack Compose interface components at runtime. Jetpack Compose is Google's toolkit for building Android and other Kotlin user interfaces.

In plain words
What is it for?
Use it when modifying the JSON-to-Compose library, its runtime UI renderer, the visual editor, the demo app, or the Ktor backend.
Why use it?
It explains how the library, editor, demo app, server, and shared code fit together so changes are made in the right place.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is jesusdmedinac/json-to-compose's own configuration. It tells Codex and OpenCode how to work on json-to-compose itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything json-to-compose configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jesusdmedinac/json-to-compose. 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/jesusdmedinac/json-to-compose/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jesusdmedinac/json-to-compose

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 json-to-compose AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jesusdmedinac/json-to-compose/agents-md/github.svg)](https://agentmods.dev/instructions/jesusdmedinac/json-to-compose/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jesusdmedinac/json-to-compose/agents-md"><img src="https://agentmods.dev/badge/instructions/jesusdmedinac/json-to-compose/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.

agentmods 80×15 button for json-to-compose AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jesusdmedinac/json-to-compose/agents-md"><img src="https://agentmods.dev/badge/instructions/jesusdmedinac/json-to-compose/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,918 This file is loaded in full into every session.
When invoked 5,918 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05918 $0.05918
Opus 5.5 $0.02367 $0.02367
Sonnet 5.5 $0.01184 $0.01184
Haiku 4.5 $0.00592 $0.00592

Measured 6d ago against content hash 7833d0c4e60f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

json-to-compose 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 6d 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 · 637 lines

How it starts

The opening of the file, as written. The whole thing — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Guide for AI Agents

This document provides essential context for AI agents to collaborate effectively on this project.

Overview

json-to-compose is a Server-Driven UI (SDUI) framework for Kotlin Multiplatform that converts JSON structures into Jetpack Compose components at runtime.

Main use case: The backend controls the application's UI without requiring app updates.

Project Structure

json-to-compose/
├── library/       → Core library (published on Maven Central v1.0.3)
├── composy/       → Visual editor web/desktop
├── composeApp/    → Multiplatform demo app
├── server/        → Ktor Backend
└── shared/        → Shared utilities

Main Module: /library

Location of core code:

library/src/commonMain/kotlin/com/jesusdmedinac/jsontocompose/
├── JsonToCompose.kt              → Entry point, CompositionLocals, router
├── model/
│   ├── ComposeNode.kt            → Serializable UI tree node
│   ├── ComposeType.kt            → Component types enum
│   ├── ComposeModifier.kt        → Serializable modifiers
│   └── NodeProperties.kt         → Component-specific props (sealed interface)
├── renderer/
│   ├── ColumnRenderer.kt         → ComposeNode.ToColumn()
│   ├── RowRenderer.kt            → ComposeNode.ToRow()
│   ├── BoxRenderer.kt            → ComposeNode.ToBox()
│   ├── TextRenderer.kt           → ComposeNode.ToText()
│   ├── ButtonRenderer.kt         → ComposeNode.ToButton()
│   ├── ImageRenderer.kt          → ComposeNode.ToImage()
│   ├── TextFieldRenderer.kt      → ComposeNode.ToTextField()
│   ├── LazyColumnRenderer.kt     → ComposeNode.ToLazyColumn()
│   ├── LazyRowRenderer.kt        → ComposeNode.ToLazyRow()
│   ├── ScaffoldRenderer.kt       → ComposeNode.ToScaffold()
│   ├── CardRenderer.kt           → ComposeNode.ToCard()
│   ├── AlertDialogRenderer.kt    → ComposeNode.ToAlertDialog()
│   ├── TopAppBarRenderer.kt      → ComposeNode.ToTopAppBar()
│   ├── CustomRenderer.kt         → ComposeNode.ToCustom()
│   ├── Alignment.kt              → String → Compose Alignment mappers
│   └── Arrangment.kt             → String → Compose Arrangement mappers
├── modifier/
│   └── ModifierMapper.kt         → Applies modifier operations
├── behavior/
│   └── Behavior.kt               → Interface for click events
└── state/
    └── StateHost.kt              → Interface for state management

Read the full file on GitHub · 637 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. 6d ago Changed · +17 lines · +191 tokens per session 7833d0c4e60f
  2. 2mo ago First seen · 620 lines · 5,727 tokens per session scan A 1bdd559bc876

Subscribe to this mod's changes

json-to-compose AGENTS.md is an instructions file published in the GitHub repository jesusdmedinac/json-to-compose (21 stars, last pushed 7d ago), licensed MIT. It adds 5,918 tokens to every session, about $0.0237 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.

Related

json-to-compose AGENTS.md compared with instructions from other repositories

json-to-compose AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
json-to-compose AGENTS.mdjesusdmedinac/json-to-composeInstructions file217d agoMITA5,918Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot