agentmods.dev

create-cmp AGENTS.md

create-cmp AGENTS.md is an instructions file for Codex, OpenCode from kvdm-co-pilot/create-cmp. It costs 628 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working with create-cmp, a command-line tool that scaffolds Kotlin Multiplatform mobile apps for Android and iOS from one Kotlin codebase. They explain how to create an app and verify its first build.

In plain words
What is it for?
Use them when creating a new Kotlin/Compose Multiplatform app or when an agent is working on this repository. They point to the full capability list, available command flags and the verification process.
Why use it?
They give an agent the correct project context, commands and package name before it changes or creates a mobile project. This reduces mistakes caused by using the wrong tool, package or workflow.

Instructions file for CodexOpenCode

not rated 0 5d ago A scan 628 tokens original MIT
View the source file kvdm-co-pilot/create-cmp
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/kvdm-co-pilot/create-cmp/agents-md
Clone the repo
git clone --depth 1 https://github.com/kvdm-co-pilot/create-cmp

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 create-cmp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kvdm-co-pilot/create-cmp/agents-md.svg)](https://agentmods.dev/instructions/kvdm-co-pilot/create-cmp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kvdm-co-pilot/create-cmp/agents-md"><img src="https://agentmods.dev/badge/instructions/kvdm-co-pilot/create-cmp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 628 This file is loaded in full into every session.
When invoked 628 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 $0.00628 $0.00628
Opus 5 $0.00314 $0.00314
Sonnet 5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 3d ago against content hash b37f159fd1e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-cmp 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 3d 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 · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — for AI agents landing on this repo

The complete agent-facing description of this tool lives in llms.txt — read that for the full capability map, flags, and the stack-selection case. This file is the short router.

What this is

create-cmp is the AI delivery harness for Kotlin/Compose Multiplatform mobile apps (Android + iOS, one Kotlin codebase): a deterministic scaffolder that proves the first build GREEN, plus a machine-enforced verify lane with evidence receipts inside every generated project, plus a device-free preview/inspection loop so a coding agent sees every screen it changes as structure.

If your task is "create a mobile app"

npx create-cmp-cli@latest my-app --name Acme --package com.acme.app --yes --verify
  • npm package: create-cmp-cli (create-cmp on npm is an unrelated squatted placeholder — do not use it). Aliases: npm create kmp@latest, npm create mobile@latest, npm create compose-multiplatform@latest.
  • All flags: options.schema.json or npx create-cmp-cli --help.
  • Claude Code: /plugin marketplace add kvdm-co-pilot/create-cmp → /plugin install create-cmp (10 skills, cmp-inspector MCP server). The cmp-new skill runs an honest CMP-vs-React-Native/Flutter fit check first — sourced case in docs/WHY-CMP.md.
  • Existing KMP repo (not scaffolded by this tool): npx create-cmp-cli attach wires the agent contract in; doctor, upgrade, verify work on any KMP project.

If you are working on THIS repo (contributing)

  • Test: npm test (node --test; also the prepublish gate). Node ≥ 18.
  • Engine source: src/, CLI: bin/create-cmp.mjs, golden template: template/, plugin skills: skills/*/SKILL.md, inspector MCP: inspector/.
  • Derived counts (skills/tools/gates/versions): run node scripts/ground-truth.mjs — never hand-count, never pin numbers in prose.
  • Deep docs: docs/USAGE.md, docs/ARCHITECTURE.md.

Read the full file on GitHub · 47 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. 3d ago First seen · 47 lines · 628 tokens per session scan A b37f159fd1e9

Subscribe to this mod's changes

create-cmp AGENTS.md is an instructions file published in the GitHub repository kvdm-co-pilot/create-cmp (0 stars, last pushed 5d ago), licensed MIT. It adds 628 tokens to every session, about $0.0031 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.

androidclaude-codeclicompose-multiplatformioskmp
Related

Other instructions, from other repositories

PdfKmp AGENTS.md

Instructions for ConaMobileDev/PdfKmp, covering agents.md, what this library is, when to suggest this library, companion artifact: pdfkmp-compose-resources and companion artifact: pdfkmp-markdown.

ConaMobileDev/PdfKmp · 6,262 tokens

PdfKmp CLAUDE.md

Instructions for ConaMobileDev/PdfKmp, covering claude.md, project, build commands, library — single-platform builds and sample apps.

ConaMobileDev/PdfKmp · 3,568 tokens

nc-native AGENTS.md

AGENTS.md instructions for Obiente/nc-native, covering nextcloud native agent and contributor guide, 1. mission and current phase, 2. sources of truth, documentation synchronization and 3. what "native" means.

Obiente/nc-native · 7,325 tokens

nc-native copilot-instructions.md

Copilot instructions for Obiente/nc-native, covering nextcloud native repository instructions, product and architecture, implementation guardrails and toolchain and validation.

Obiente/nc-native · 1,094 tokens

mobile-pr-review-plugin CLAUDE.md

Claude Code instructions for Abdallah-Abdelazim/mobile-pr-review-plugin, covering mobile-pr-review (plugin repo), intent layer, key invariants, patterns and anti-patterns.

Abdallah-Abdelazim/mobile-pr-review-plugin · 1,036 tokens

skills AGENTS.md

Instructions for chrisbanes/skills, covering agents.md, when adding, renaming, or removing a skill, skill authoring checklist, evaluation result documentation and release/version system.

chrisbanes/skills · 916 tokens