compose-android-template AGENTS.md

A repository guide for an Android app built with Kotlin and Jetpack Compose, Google’s toolkit for describing Android screens in code. It explains where to find task context and how the project organizes shared, Android, and generated code.

In plain words
What is it for?
Use it when changing Android or Kotlin code, Compose screens, Gradle setup, shared logic, dependencies, tests, or project documentation.
Why use it?
It prevents agents from using the wrong build tools, Java version, dependency location, or module boundary. It also helps protect unrelated work and generated files from accidental edits.

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/ashtanko/compose-android-template/agents-md
Clone the repo
git clone --depth 1 https://github.com/ashtanko/compose-android-template

Made for: Codex, OpenCode.

Per session 783 This file is loaded in full into every session.
When invoked 783 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 $0.00783 $0.00783
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2d ago against content hash 3fca7b13b712, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compose-android-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 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 · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository agent guide

This file is the canonical entry point for coding agents working in this repository. It applies to the entire tree unless a nested AGENTS.md says otherwise.

Start here

  • Read .agents/README.md for the task-specific context map.
  • Load only the relevant reference or skill; do not pull every AI document into context.
  • Treat README.md as the human-facing product overview, not as the source of agent workflow rules.

Repository rules

  • Use the Gradle wrapper and JDK 21. Do not rely on a globally installed Gradle.
  • Preserve unrelated work in a dirty worktree. Inspect the diff before editing and never clean up changes you did not make.
  • Keep dependency and plugin versions in gradle/libs.versions.toml; do not hardcode versions in module build files.
  • Reuse the convention plugins in build-logic/convention instead of duplicating Android, Kotlin, Compose, Hilt, Room, lint, coverage, or formatting setup.
  • Put platform-independent logic in a Kotlin/JVM module. Keep Android APIs and Compose code in Android modules.
  • Do not edit generated output under build/, .gradle/, .kotlin/, IDE state, reports, dependency snapshots, screenshot goldens, or baselines unless the task explicitly requires it.
  • Never commit local.properties, production signing credentials, production keystores, environment files, or real secrets. The repository's template debug keystore may remain. Preserve the existing CI environment-variable contract for signing.
  • Follow .editorconfig, Detekt, KtLint, and Spotless. Use trailing commas in multi-line parameter lists, argument lists, and collection literals (enabled via .editorconfig's ij_kotlin_allow_trailing_comma* and enforced by KtLint). Prefer immutable UI state and lifecycle-aware Flow collection in Compose code.

Working method

  1. Inspect the target module, neighboring implementations, its build.gradle.kts, and the current diff.
  2. Make the smallest coherent change that follows existing package and module boundaries.
  3. Add or update tests with behavior changes. Use previews or screenshot tests for meaningful visual state changes where the module already supports them.
  4. Run the narrowest useful checks first, then broaden checks in proportion to the change. See .agents/reference/commands.md.
  5. Report changed files, checks run, and anything not verified. Never claim a check passed if it was not run.

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 783 tokens per session scan A 3fca7b13b712

Subscribe to this mod's changes

compose-android-template AGENTS.md is an instructions file published in the GitHub repository ashtanko/compose-android-template (10 stars, last pushed 5d ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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.

Related

Other instructions, from other repositories

sceneview copilot-instructions.md

Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.

sceneview/sceneview · 1,023 tokens

sceneview CLAUDE.md

Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.

sceneview/sceneview · 984 tokens

ConsultMe CLAUDE.md

Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.

Tarek-Bohdima/ConsultMe · 3,021 tokens

ukulele-companion AGENTS.md

Instructions for baijum/ukulele-companion, covering agents.md -- ai agent instructions for ukulele companion, project overview, tech stack, package structure and android app (app/src/main/java/com/baijum/ukufretboard/).

baijum/ukulele-companion · 3,289 tokens

AppBootstrapAI CLAUDE.md

Instructions for kelvinkosbab/AppBootstrapAI, covering claude.md, project overview, what's in the box, how to onboard this into a new app project and update an already-managed repo — never a plain re-install.

kelvinkosbab/AppBootstrapAI · 11,402 tokens

AppBootstrapAI AGENTS.md

Instructions for kelvinkosbab/AppBootstrapAI, covering agents.md — operating appbootstrapai, golden path — do this, the three situations recommend resolves, what recommend keys on (framework → feature category) and scaffolding a local swift package (separate tool).

kelvinkosbab/AppBootstrapAI · 1,333 tokens